category stringclasses 19
values | ctf_task_type stringclasses 7
values | dataset stringclasses 1
value | id stringlengths 29 29 | messages listlengths 3 3 | metadata unknown | source_dataset stringclasses 3
values | source_path stringlengths 0 93 | split stringclasses 1
value | type stringclasses 1
value |
|---|---|---|---|---|---|---|---|---|---|
executable | ai | ctf-dataset | ctf-lora-9797f67b7de2e2d5c8b5 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/pe/pe-excutable.md` 中的章节「IMAGE_OPTIONAL_HEADER」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源... | {
"category": "executable",
"chars": 2104,
"chunk_count": 2,
"chunk_index": 1,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "IMAGE_OPTIONAL_HEADER",
"heading_path": [
"PE 文件格式",
"PE文件头",
"IMAGE_NT_HEADERS",
"IMAGE_OPTIONAL_HEADER"
],
"original_id": "docs-6b5bfefde1ea64523872",
... | docs_distilled_v1 | executable/pe/pe-excutable.md | train | ctf_lora_sft |
executable | ai | ctf-dataset | ctf-lora-99d4bc439d339c51232b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/pe/pe-excutable.md` 中的章节「IMAGE_OPTIONAL_HEADER」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源... | {
"category": "executable",
"chars": 4992,
"chunk_count": 2,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "IMAGE_OPTIONAL_HEADER",
"heading_path": [
"PE 文件格式",
"PE文件头",
"IMAGE_NT_HEADERS",
"IMAGE_OPTIONAL_HEADER"
],
"original_id": "docs-c494d3dfa494ccefc695",
... | docs_distilled_v1 | executable/pe/pe-excutable.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-9b51429f77b353c7de92 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/blockcipher/mode/cbc.md` 中的章节「例题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/bloc... | {
"category": "crypto",
"chars": 2190,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "例题",
"heading_path": [
"CBC",
"攻击",
"字节反转攻击",
"例题"
],
"original_id": "docs-c1f0a8ade8c0a8dbd345",
"original_line": 331,
"original_split": "train",
"rec... | docs_distilled_v1 | crypto/blockcipher/mode/cbc.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-9b5893955d5fcace457b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/heap-flags.md` 中的章节「检测ForgeFlags字段」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"... | {
"category": "reverse",
"chars": 1591,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "检测ForgeFlags字段",
"heading_path": [
"Heap Flags",
"检测ForgeFlags字段"
],
"original_id": "docs-78c0db9cafbc157a7aaf",
"original_line": 1518,
"original_split": "train... | docs_distilled_v1 | reverse/platform/windows/anti-debug/heap-flags.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-9c32bc1a992194e9cf55 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/identify-encode-encryption/introduction.md` 中的章节「python解密脚本」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"con... | {
"category": "reverse",
"chars": 1207,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "python解密脚本",
"heading_path": [
"常见加密算法和编码识别",
"RC4",
"python解密脚本"
],
"original_id": "docs-d1bfb9789cf32c4618d4",
"original_line": 1475,
"original_split": "t... | docs_distilled_v1 | reverse/identify-encode-encryption/introduction.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-9c8ba7aae1232a2cf953 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/multi-agent-orchestration/knowledge-sharing/introduction.md` 中的章节「简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role"... | {
"category": "ai",
"chars": 1078,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "简介",
"heading_path": [
"简介"
],
"original_id": "docs-bcd05e9620beb733d4af",
"original_line": 24,
"original_split": "train",
"record_type": "doc_section_distillation",
... | docs_distilled_v1 | ai/ai-for-security/agent/multi-agent-orchestration/knowledge-sharing/introduction.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-9dd1b6b4cf87752163a5 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「CTF 与 AI Agent」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "ai",
"chars": 1382,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "CTF 与 AI Agent",
"heading_path": [
"AI Agent",
"CTF 与 AI Agent"
],
"original_id": "docs-fa6b29c18970ab94e7ce",
"original_line": 10,
"original_split": "train",
"rec... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-9eb668566a4c6c30946f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/fake-vtable-exploit.md` 中的章节「基本信息」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "pwn",
"chars": 424,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 22,
"ctf_task_type": "ai",
"heading": "基本信息",
"heading_path": [
"伪造vtable劫持程序流程",
"2018 HCTF the_end",
"基本信息"
],
"original_id": "docs-1b78493b922d0f4f7959",
"original_line": 63,
"original_split": "val... | docs_distilled_v1 | pwn/linux/user-mode/io-file/fake-vtable-exploit.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-a22e5ef9b729abcf5f66 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/the-heap.md` 中的章节「The Heap」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content"... | {
"category": "reverse",
"chars": 317,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "The Heap",
"heading_path": [
"The Heap"
],
"original_id": "docs-0c92a42f9ecf97769387",
"original_line": 1532,
"original_split": "train",
"record_type": "doc_sectio... | docs_distilled_v1 | reverse/platform/windows/anti-debug/the-heap.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-a4a66f5fedad963ba950 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/blockcipher/des.md` 中的章节「-- coding: utf-8 --」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs... | {
"category": "crypto",
"chars": 3325,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "-- coding: utf-8 --",
"heading_path": [
"-- coding: utf-8 --"
],
"original_id": "docs-42fb6e8ca42ecd4af652",
"original_line": 321,
"original_split": "train",
"reco... | docs_distilled_v1 | crypto/blockcipher/des.md | train | ctf_lora_sft |
ics | ai | ctf-dataset | ctf-lora-a4f69ad2766dc46edd20 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ics/ctfs.md` 中的章节「国内工控比赛考察点」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/ics/ctfs.md`\n标题：ICS_CT... | {
"category": "ics",
"chars": 603,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "国内工控比赛考察点",
"heading_path": [
"ICS_CTF 竞赛",
"国内工控比赛考察点"
],
"original_id": "docs-69bbc6147002cb86e265",
"original_line": 505,
"original_split": "train",
"record_typ... | docs_distilled_v1 | ics/ctfs.md | train | ctf_lora_sft |
android | ai | ctf-dataset | ctf-lora-a61778ff63e806b74b5a | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/android/basic_operating_mechanism/native_layer/so.md` 中的章节「dvmLoadNativeCode」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{... | {
"category": "android",
"chars": 4969,
"chunk_count": 2,
"chunk_index": 1,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "dvmLoadNativeCode",
"heading_path": [
"so 介绍",
"核心加载流程",
"dvmLoadNativeCode"
],
"original_id": "docs-b7855b96735068dde220",
"original_line": 75,
"original_s... | docs_distilled_v1 | android/basic_operating_mechanism/native_layer/so.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-a6da3879897dbd76f085 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/tools/constraint/z3.md` 中的章节「简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/too... | {
"category": "reverse",
"chars": 260,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "简介",
"heading_path": [
"z3",
"简介"
],
"original_id": "docs-26c192bfad5e045577fa",
"original_line": 1551,
"original_split": "train",
"record_type": "doc_section_... | docs_distilled_v1 | reverse/tools/constraint/z3.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-a7a7fe55069d584da10d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/ntglobalflag.md` 中的章节「关于NtGlobalFlag」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
... | {
"category": "reverse",
"chars": 300,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "关于NtGlobalFlag",
"heading_path": [
"NtGlobalFlag",
"关于NtGlobalFlag"
],
"original_id": "docs-66df7f4b7783514a6b40",
"original_line": 1522,
"original_split": "trai... | docs_distilled_v1 | reverse/platform/windows/anti-debug/ntglobalflag.md | train | ctf_lora_sft |
android | ai | ctf-dataset | ctf-lora-aada16968d760aa5e789 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/android/basic_operating_mechanism/native_layer/so.md` 中的章节「loadLibrary 加载流程」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
... | {
"category": "android",
"chars": 2046,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "loadLibrary 加载流程",
"heading_path": [
"so 介绍",
"loadLibrary 加载流程"
],
"original_id": "docs-cbdb41227a387f287dc3",
"original_line": 70,
"original_split": "train",
... | docs_distilled_v1 | android/basic_operating_mechanism/native_layer/so.md | train | ctf_lora_sft |
assembly | ai | ctf-dataset | ctf-lora-aaf2cf9aa9862ba8d8b4 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/assembly/risc-v/readme.md` 中的章节「（2）常见立即数指令（I 型）」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/ass... | {
"category": "assembly",
"chars": 729,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "（2）常见立即数指令（I 型）",
"heading_path": [
"Risc-V",
"0x03 常见指令",
"（2）常见立即数指令（I 型）"
],
"original_id": "docs-a484634076bc6faa6f21",
"original_line": 116,
"original_... | docs_distilled_v1 | assembly/risc-v/readme.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-ae54646232dd5073ba36 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`do... | {
"category": "ai",
"chars": 833,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "简介",
"heading_path": [
"简介"
],
"original_id": "docs-68af0d86ee3243921ed1",
"original_line": 13,
"original_split": "train",
"record_type": "doc_section_distillation",
... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
blockchain | ai | ctf-dataset | ctf-lora-b49464a16bab643374ab | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/challenges.md` 中的章节「Public Blockchain」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/bl... | {
"category": "blockchain",
"chars": 211,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "Public Blockchain",
"heading_path": [
"Blockchain Security Challenges",
"Blockchain Security Challenges in CTF",
"Public Blockchain"
],
"original_id": "docs-e... | docs_distilled_v1 | blockchain/challenges.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-b4c0c286605f9e093315 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「基本规则」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduction/mode.m... | {
"category": "introduction",
"chars": 522,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "基本规则",
"heading_path": [
"CTF 竞赛模式简介",
"攻防模式 - Attack & Defense",
"基本规则"
],
"original_id": "docs-055c711f8cf6994dde3a",
"original_line": 532,
"original_... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
web | ai | ctf-dataset | ctf-lora-b59ee07e73de1eaa16db | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/web/introduction.md` 中的章节「XSCH」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/web/introduction.md`... | {
"category": "web",
"chars": 230,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "XSCH",
"heading_path": [
"Web 简介",
"XSCH"
],
"original_id": "docs-393f22a630e79d92615d",
"original_line": 1593,
"original_split": "train",
"record_type": "doc_sect... | docs_distilled_v1 | web/introduction.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-b5d7cde0326cbdd2115b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/security-for-ai/introduction.md` 中的章节「简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/ai/secu... | {
"category": "ai",
"chars": 180,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "简介",
"heading_path": [
"Security for AI",
"简介"
],
"original_id": "docs-d29b97c3f8c4c0fd6210",
"original_line": 25,
"original_split": "train",
"record_type": "doc_se... | docs_distilled_v1 | ai/security-for-ai/introduction.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-b761bd09f4a8e133876b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/linux/detect-dbg.md` 中的章节「Detecting debugging」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content"... | {
"category": "reverse",
"chars": 329,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Detecting debugging",
"heading_path": [
"Detecting debugging"
],
"original_id": "docs-ef6c2e9fbbcc39c70661",
"original_line": 1491,
"original_split": "train",
"rec... | docs_distilled_v1 | reverse/platform/linux/detect-dbg.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-b79d3d1098d7797264f9 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「6. 调用 Agent Loop」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"con... | {
"category": "ai",
"chars": 504,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "6. 调用 Agent Loop",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"6. 调用 Agent Loop"
],
"original_id": "docs-ea0d545a6d5ffece017e",
"original_line": 20,
"original... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-b8695c8f631cf44bffe0 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/experience.md` 中的章节「线下攻防经验小结」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduct... | {
"category": "introduction",
"chars": 255,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "线下攻防经验小结",
"heading_path": [
"线下攻防经验小结"
],
"original_id": "docs-f83aba9b40b820c2c50e",
"original_line": 520,
"original_split": "train",
"record_type": "doc_se... | docs_distilled_v1 | introduction/experience.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-b94065df9f023191fb1e | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/linux/detect-dbg.md` 中的章节「gdb test_debug」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源... | {
"category": "reverse",
"chars": 545,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "gdb test_debug",
"heading_path": [
"gdb test_debug"
],
"original_id": "docs-77100585155509d3d976",
"original_line": 1494,
"original_split": "train",
"record_type":... | docs_distilled_v1 | reverse/platform/linux/detect-dbg.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-be310b4eda966a9ad8f6 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/basic-knowledge/mm.md` 中的章节「AddressSpace：不同类型的 Guest 地址空间」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
}... | {
"category": "pwn",
"chars": 640,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "AddressSpace：不同类型的 Guest 地址空间",
"heading_path": [
"QEMU 内存管理",
"Guest VM 视角（GPA）",
"AddressSpace：不同类型的 Guest 地址空间"
],
"original_id": "docs-d51cec35ba3c43ec2334",
"... | docs_distilled_v1 | pwn/virtualization/qemu/basic-knowledge/mm.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-bfdf5a4166431e524813 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/classical/polyalphabetic.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/... | {
"category": "crypto",
"chars": 334,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "原理",
"heading_path": [
"多表代换加密",
"AutokeyCipher",
"原理"
],
"original_id": "docs-7b238e19770c08cc9f8d",
"original_line": 384,
"original_split": "train",
"reco... | docs_distilled_v1 | crypto/classical/polyalphabetic.md | train | ctf_lora_sft |
executable | ai | ctf-dataset | ctf-lora-c02d9fb095deafe7df39 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/elf/structure/sections.md` 中的章节「Sections」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs... | {
"category": "executable",
"chars": 1910,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Sections",
"heading_path": [
"Sections"
],
"original_id": "docs-8ae24cf42ffc36b78f1c",
"original_line": 483,
"original_split": "train",
"record_type": "doc_sec... | docs_distilled_v1 | executable/elf/structure/sections.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-c04a3ea228109d52209b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/experience.md` 中的章节「服务 patch 与防御」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/intro... | {
"category": "introduction",
"chars": 456,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "服务 patch 与防御",
"heading_path": [
"线下攻防经验小结",
"服务 patch 与防御"
],
"original_id": "docs-ef6ec31ac37951f54329",
"original_line": 523,
"original_split": "train",
... | docs_distilled_v1 | introduction/experience.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-c07b94707da50cc71330 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/basic-knowledge/io-virtualization.md` 中的章节「VRing：virtqueue 的基本结构」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
... | {
"category": "pwn",
"chars": 925,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "VRing：virtqueue 的基本结构",
"heading_path": [
"IO 虚拟化",
"软件半虚拟化 - virtio",
"VRing：virtqueue 的基本结构"
],
"original_id": "docs-c6b466b2a667e6fb7a21",
"original_line": 1412... | docs_distilled_v1 | pwn/virtualization/basic-knowledge/io-virtualization.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-c107f11fcfc0c8b168cf | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/tools/constraint/z3.md` 中的章节「求解」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/too... | {
"category": "reverse",
"chars": 1584,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "求解",
"heading_path": [
"z3",
"例题：GWCTF 2019 - xxor",
"求解"
],
"original_id": "docs-5132e6944d45cc20396d",
"original_line": 1557,
"original_split": "train",
... | docs_distilled_v1 | reverse/tools/constraint/z3.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-c45d63a2801a81097a03 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/mitigation/canary.md` 中的章节「one-by-one 爆破 Canary」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"con... | {
"category": "pwn",
"chars": 631,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "one-by-one 爆破 Canary",
"heading_path": [
"Bypass Canary",
"one-by-one 爆破 Canary"
],
"original_id": "docs-8d847d3bfa06fe0be657",
"original_line": 1218,
"original_spli... | docs_distilled_v1 | pwn/linux/user-mode/mitigation/canary.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-c46b12978859bc816db8 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/basic-knowledge/cpu-virtualization.md` 中的章节「扫描 & 修补」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"... | {
"category": "pwn",
"chars": 671,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "扫描 & 修补",
"heading_path": [
"CPU 虚拟化",
"纯软件实现 CPU 虚拟化",
"扫描 & 修补"
],
"original_id": "docs-41c3d29454b34be7f4cf",
"original_line": 1402,
"original_split": "train"... | docs_distilled_v1 | pwn/virtualization/basic-knowledge/cpu-virtualization.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-c50c79f5a74043b1bd1c | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/linux/detect-dbg.md` 中的章节「gdb test_debug」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源... | {
"category": "reverse",
"chars": 522,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "gdb test_debug",
"heading_path": [
"gdb test_debug"
],
"original_id": "docs-34e73c11c14aaf3536f0",
"original_line": 1493,
"original_split": "train",
"record_type":... | docs_distilled_v1 | reverse/platform/linux/detect-dbg.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-c790a228e04b8583cbd4 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/tools/constraint/z3.md` 中的章节「常量表示」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/t... | {
"category": "reverse",
"chars": 308,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "常量表示",
"heading_path": [
"z3",
"基本用法",
"常量表示"
],
"original_id": "docs-549288332508095873d2",
"original_line": 1553,
"original_split": "train",
"record_type... | docs_distilled_v1 | reverse/tools/constraint/z3.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-c90198f53bb8d9cb8536 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/introduction.md` 中的章节「密码学简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/introduct... | {
"category": "crypto",
"chars": 1609,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "密码学简介",
"heading_path": [
"密码学简介"
],
"original_id": "docs-9758e303000b538eede5",
"original_line": 201,
"original_split": "train",
"record_type": "doc_section_disti... | docs_distilled_v1 | crypto/introduction.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-cd6ccdc663175cc6b1d3 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「概述」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduction/mode.md`... | {
"category": "introduction",
"chars": 629,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "概述",
"heading_path": [
"CTF 竞赛模式简介",
"攻防模式 - Attack & Defense",
"概述"
],
"original_id": "docs-a3040061e3a30367e388",
"original_line": 531,
"original_spli... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-ceab62a4ec182b6a22c8 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/summary/get-address.md` 中的章节「Dump some useful offsets, given a libc ID. You can also provide your own names to dump.」蒸馏为可用于训练安全模型的结构化知识。请输出来源... | {
"category": "pwn",
"chars": 241,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Dump some useful offsets, given a libc ID. You can also provide your own names to dump.",
"heading_path": [
"Dump some useful offsets, given a libc ID. You can also provide your... | docs_distilled_v1 | pwn/linux/user-mode/summary/get-address.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-ceb60a3d33475a9b6342 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「3. 工具系统（Tools）」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "ai",
"chars": 185,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "3. 工具系统（Tools）",
"heading_path": [
"AI Agent",
"AI Agent 的系统架构",
"3. 工具系统（Tools）"
],
"original_id": "docs-a3f6f1121eaea3cfc280",
"original_line": 5,
"original_spl... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
executable | ai | ctf-dataset | ctf-lora-d243d81e20f70911a933 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/elf/linking/symbol-resolve.md` 中的章节「_dl_fixup」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：... | {
"category": "executable",
"chars": 4366,
"chunk_count": 2,
"chunk_index": 1,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "_dl_fixup",
"heading_path": [
"endif",
"_dl_fixup"
],
"original_id": "docs-b912a750ddd67eec0afc",
"original_line": 455,
"original_split": "train",
"record_... | docs_distilled_v1 | executable/elf/linking/symbol-resolve.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-d2c01b570faa10007312 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/classical/others.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/classica... | {
"category": "crypto",
"chars": 307,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "原理",
"heading_path": [
"其它类型加密",
"栅栏密码",
"原理"
],
"original_id": "docs-4cb9a6d2fb96be234740",
"original_line": 368,
"original_split": "train",
"record_type":... | docs_distilled_v1 | crypto/classical/others.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-d2df7dbcb77628b730ff | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/environment/build-qemu-dev.md` 中的章节「Qemu 中 PCI 设备的编写」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{... | {
"category": "pwn",
"chars": 1859,
"chunk_count": 2,
"chunk_index": 1,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Qemu 中 PCI 设备的编写",
"heading_path": [
"编写 QEMU 模拟设备",
"Qemu 中 PCI 设备的编写"
],
"original_id": "docs-61ccc47a46a1be678665",
"original_line": 1435,
"original_split": "tra... | docs_distilled_v1 | pwn/virtualization/qemu/environment/build-qemu-dev.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-d4b14250f028ed52a26c | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/exploitation/intro.md` 中的章节「交互方式」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：... | {
"category": "pwn",
"chars": 5193,
"chunk_count": 2,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "交互方式",
"heading_path": [
"QEMU 逃逸入门",
"例题：BlizzardCTF2017 - Strng",
"交互方式"
],
"original_id": "docs-5b190b75b5d4629e3254",
"original_line": 78,
"original_split":... | docs_distilled_v1 | pwn/virtualization/qemu/exploitation/intro.md | train | ctf_lora_sft |
blockchain | ai | ctf-dataset | ctf-lora-d588e98cd502e72dc7b4 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/publicblockchain/weaknesses.md` 中的章节「51% attack」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来... | {
"category": "blockchain",
"chars": 455,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "51% attack",
"heading_path": [
"Blockchain Weaknesses",
"Double-spending attack",
"51% attack"
],
"original_id": "docs-cd4d1a46d8008d0d908b",
"original_line... | docs_distilled_v1 | blockchain/publicblockchain/weaknesses.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-d60eed0ed509023a31bd | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/basic-knowledge/basic-knowledge.md` 中的章节「基本模型」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"conten... | {
"category": "pwn",
"chars": 1939,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "基本模型",
"heading_path": [
"虚拟化技术简介",
"系统虚拟化概述",
"基本模型"
],
"original_id": "docs-f3574b022a5decbaff70",
"original_line": 1397,
"original_split": "train",
"record... | docs_distilled_v1 | pwn/virtualization/basic-knowledge/basic-knowledge.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-d7bdf1cbc2abbeaa3b93 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/basic-knowledge/mm.md` 中的章节「RAMBlock：MR 对应的 Host 虚拟内存」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
... | {
"category": "pwn",
"chars": 2156,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "RAMBlock：MR 对应的 Host 虚拟内存",
"heading_path": [
"QEMU 内存管理",
"host VMM 视角（HVA）",
"RAMBlock：MR 对应的 Host 虚拟内存"
],
"original_id": "docs-c5b062574cc5a0915b8e",
"origina... | docs_distilled_v1 | pwn/virtualization/qemu/basic-knowledge/mm.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-d894383429559704c9fe | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/asymmetric/discrete-log/discrete-log.md` 中的章节「Pohlig-Hellman algorithm」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
... | {
"category": "crypto",
"chars": 776,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Pohlig-Hellman algorithm",
"heading_path": [
"离散对数",
"离散对数求解方式",
"Pohlig-Hellman algorithm"
],
"original_id": "docs-8d2e3bceeafe35801078",
"original_line": 204,... | docs_distilled_v1 | crypto/asymmetric/discrete-log/discrete-log.md | train | ctf_lora_sft |
assembly | ai | ctf-dataset | ctf-lora-d8a96eb5f0391ab97667 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/assembly/mips/readme.md` 中的章节「0x2 指令 Instruction」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/as... | {
"category": "assembly",
"chars": 5014,
"chunk_count": 4,
"chunk_index": 1,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "0x2 指令 Instruction",
"heading_path": [
"MIPS",
"0x2 指令 Instruction"
],
"original_id": "docs-2cf459980a45a58bee8f",
"original_line": 108,
"original_split": "tra... | docs_distilled_v1 | assembly/mips/readme.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-d8de527079a5de0b2cfe | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/fake-vtable-exploit.md` 中的章节「思路：」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": ... | {
"category": "pwn",
"chars": 2892,
"chunk_count": 2,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "思路：",
"heading_path": [
"伪造vtable劫持程序流程",
"2018 HCTF the_end",
"思路："
],
"original_id": "docs-fa7666606ce8730217af",
"original_line": 1202,
"original_split": "tr... | docs_distilled_v1 | pwn/linux/user-mode/io-file/fake-vtable-exploit.md | train | ctf_lora_sft |
android | ai | ctf-dataset | ctf-lora-de05cf1cca59b29f75bb | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/android/basic_operating_mechanism/native_layer/so.md` 中的章节「dvmLoadNativeCode」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{... | {
"category": "android",
"chars": 4520,
"chunk_count": 2,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "dvmLoadNativeCode",
"heading_path": [
"so 介绍",
"核心加载流程",
"dvmLoadNativeCode"
],
"original_id": "docs-ac16eaf3528aec654490",
"original_line": 74,
"original_s... | docs_distilled_v1 | android/basic_operating_mechanism/native_layer/so.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-de3e5821043e5a40cf63 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「解题模式 - Jeopardy」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduc... | {
"category": "introduction",
"chars": 467,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "解题模式 - Jeopardy",
"heading_path": [
"CTF 竞赛模式简介",
"解题模式 - Jeopardy"
],
"original_id": "docs-4db0b8f1c9a0a64b76c1",
"original_line": 526,
"original_split": "... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-e1ba5bae62be211a0aca | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/environment/build-qemu-dev.md` 中的章节「Qemu 中 PCI 设备的编写」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{... | {
"category": "pwn",
"chars": 5150,
"chunk_count": 2,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Qemu 中 PCI 设备的编写",
"heading_path": [
"编写 QEMU 模拟设备",
"Qemu 中 PCI 设备的编写"
],
"original_id": "docs-e9a009015f8e47fcff34",
"original_line": 1434,
"original_split": "tra... | docs_distilled_v1 | pwn/virtualization/qemu/environment/build-qemu-dev.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-e259153d3801eaae59f3 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/integeroverflow/introduction.md` 中的章节「错误的类型转换」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"conte... | {
"category": "pwn",
"chars": 1018,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "错误的类型转换",
"heading_path": [
"gdb a.out",
"错误的类型转换"
],
"original_id": "docs-f9a778640addd87f60f3",
"original_line": 62,
"original_split": "validation",
"record_typ... | docs_distilled_v1 | pwn/linux/user-mode/integeroverflow/introduction.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-e2a217178c88e74ec04a | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/basic-knowledge/io-virtualization.md` 中的章节「平台设备模拟（Platform device emulation）」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"rol... | {
"category": "pwn",
"chars": 486,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "平台设备模拟（Platform device emulation）",
"heading_path": [
"IO 虚拟化",
"基本模型",
"平台设备模拟（Platform device emulation）"
],
"original_id": "docs-269f682c8be5fafe4f4c",
"origina... | docs_distilled_v1 | pwn/virtualization/basic-knowledge/io-virtualization.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-e3fc705d976ad332768f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「5. 构建 LLM-based 的 Agent Loop」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
... | {
"category": "ai",
"chars": 1970,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "5. 构建 LLM-based 的 Agent Loop",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"5. 构建 LLM-based 的 Agent Loop"
],
"original_id": "docs-9e4c23814beb6edb9ee7",
"origin... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-e5d13b8ff55caca0740d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/traffic/fix.md` 中的章节「PCAP文件结构」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/traffic/fix... | {
"category": "misc",
"chars": 1563,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "PCAP文件结构",
"heading_path": [
"PCAP 文件修复",
"PCAP文件结构"
],
"original_id": "docs-c650b62e326a603ce204",
"original_line": 596,
"original_split": "train",
"record_type... | docs_distilled_v1 | misc/traffic/fix.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-e7d555a9c9cd9cd4e1d6 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/tools/constraint/z3.md` 中的章节「逆向分析」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/t... | {
"category": "reverse",
"chars": 2337,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "逆向分析",
"heading_path": [
"z3",
"例题：GWCTF 2019 - xxor",
"逆向分析"
],
"original_id": "docs-bf07fbd0afade14853b0",
"original_line": 1556,
"original_split": "train... | docs_distilled_v1 | reverse/tools/constraint/z3.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-e98c082d18cfa8f7736b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/zwsetinformationthread.md` 中的章节「关于ZwSetInformationThread」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role":... | {
"category": "reverse",
"chars": 778,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "关于ZwSetInformationThread",
"heading_path": [
"ZwSetInformationThread",
"关于ZwSetInformationThread"
],
"original_id": "docs-83b1e9be6a9e91fae672",
"original_line": 1... | docs_distilled_v1 | reverse/platform/windows/anti-debug/zwsetinformationthread.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-ebe2bc179917fcd61367 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/a... | {
"category": "ai",
"chars": 1063,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "简介",
"heading_path": [
"AI Agent",
"简介"
],
"original_id": "docs-077bc02d470e0ada0fcd",
"original_line": 2,
"original_split": "train",
"record_type": "doc_section_d... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-ed175716c77131e9b59e | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/introduction.md` 中的章节「fclose」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：... | {
"category": "pwn",
"chars": 513,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "fclose",
"heading_path": [
"else",
"fclose"
],
"original_id": "docs-951edf0a77336a19bb60",
"original_line": 1212,
"original_split": "train",
"record_type": "doc_se... | docs_distilled_v1 | pwn/linux/user-mode/io-file/introduction.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-efb8061c2d19e849bbee | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「网络环境」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduction/mode.m... | {
"category": "introduction",
"chars": 342,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "网络环境",
"heading_path": [
"CTF 竞赛模式简介",
"攻防模式 - Attack & Defense",
"网络环境"
],
"original_id": "docs-fc2accfcc9c3658016ae",
"original_line": 533,
"original_... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-f2c9285f27de67c43388 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/checkremotedebuggerpresent.md` 中的章节「如何绕过」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{... | {
"category": "reverse",
"chars": 623,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "如何绕过",
"heading_path": [
"CheckRemoteDebuggerPresent",
"如何绕过"
],
"original_id": "docs-886e9d5e7cc75114fc44",
"original_line": 1503,
"original_split": "train",
... | docs_distilled_v1 | reverse/platform/windows/anti-debug/checkremotedebuggerpresent.md | train | ctf_lora_sft |
android | ai | ctf-dataset | ctf-lora-f35205f688745fc25d8b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/android/basic_operating_mechanism/native_layer/so.md` 中的章节「nativeload」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"c... | {
"category": "android",
"chars": 2425,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "nativeload",
"heading_path": [
"so 介绍",
"核心加载流程",
"nativeload"
],
"original_id": "docs-dbc122e04494ff450f4c",
"original_line": 73,
"original_split": "train"... | docs_distilled_v1 | android/basic_operating_mechanism/native_layer/so.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-f4054cf831f9e05b5430 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/obfuscate/junk-code.md` 中的章节「逆向分析」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/o... | {
"category": "reverse",
"chars": 4906,
"chunk_count": 3,
"chunk_index": 1,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "逆向分析",
"heading_path": [
"花指令",
"例题：N1CTF2020 - oflo",
"逆向分析"
],
"original_id": "docs-0d3c8c43f1350ef14f11",
"original_line": 1481,
"original_split": "train... | docs_distilled_v1 | reverse/obfuscate/junk-code.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-fc160bbf5c9564f9b4f6 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/mitigation/canary.md` 中的章节「Canary 实现原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来... | {
"category": "pwn",
"chars": 2119,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "Canary 实现原理",
"heading_path": [
"Canary",
"Canary 原理",
"Canary 实现原理"
],
"original_id": "docs-564457d7e96dbed1b6ef",
"original_line": 1216,
"original_split": "tr... | docs_distilled_v1 | pwn/linux/user-mode/mitigation/canary.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-fedb7b2aba23f4a91033 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「从“模型调用”到“系统行为”」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "ai",
"chars": 383,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "从“模型调用”到“系统行为”",
"heading_path": [
"AI Agent",
"从“模型调用”到“系统行为”"
],
"original_id": "docs-5ea5354353a1bda5a48c",
"original_line": 8,
"original_split": "train",
"recor... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
misc_pwn | ai | ctf-dataset | ctf-lora-0ae422c50a5bf4def789 | [
{
"content": "你是 CTF pwn、Linux kernel exploit 与二进制安全训练数据蒸馏助手。回答必须基于给定本地材料，保留关键路径、函数名、偏移、保护信息、利用原语和验证状态；不要编造材料中没有出现的事实。",
"role": "system"
},
{
"content": "根据 `其它/2024ycb logger` 目录下的 writeup 和 exploit 示例，蒸馏一条训练样本：总结题目、漏洞点、利用链、关键代码和验证状态。",
"role": "user"
},
{
"content": "## 题目路径\n`其它/2024... | {
"category": "misc_pwn",
"ctf_score": 26,
"ctf_task_type": "ai",
"original_id": "pwn101-pair-cb0d16340bc20425",
"original_line": 437,
"original_split": "train",
"record_type": "writeup_exploit_pair",
"source_dataset": "pwn101_distilled_v1",
"source_path": "其它/2024ycb logger",
"split": "train",
"s... | pwn101_distilled_v1 | 其它/2024ycb logger | train | ctf_lora_sft |
misc_pwn | ai | ctf-dataset | ctf-lora-26c9a6d2999661eb95f6 | [
{
"content": "你是 CTF pwn、Linux kernel exploit 与二进制安全训练数据蒸馏助手。回答必须基于给定本地材料，保留关键路径、函数名、偏移、保护信息、利用原语和验证状态；不要编造材料中没有出现的事实。",
"role": "system"
},
{
"content": "根据 `其它/2024ccb anote` 目录下的 writeup 和 exploit 示例，蒸馏一条训练样本：总结题目、漏洞点、利用链、关键代码和验证状态。",
"role": "user"
},
{
"content": "## 题目路径\n`其它/2024c... | {
"category": "misc_pwn",
"ctf_score": 26,
"ctf_task_type": "ai",
"original_id": "pwn101-pair-f1f7853138c1ff14",
"original_line": 435,
"original_split": "train",
"record_type": "writeup_exploit_pair",
"source_dataset": "pwn101_distilled_v1",
"source_path": "其它/2024ccb anote",
"split": "train",
"sp... | pwn101_distilled_v1 | 其它/2024ccb anote | train | ctf_lora_sft |
misc_vuln | ai | ctf-dataset | ctf-lora-a963fe1ae6963a5682f4 | [
{
"content": "你是 CTF pwn、Linux kernel exploit 与二进制安全训练数据蒸馏助手。回答必须基于给定本地材料，保留关键路径、函数名、偏移、保护信息、利用原语和验证状态；不要编造材料中没有出现的事实。",
"role": "system"
},
{
"content": "根据 `其它漏洞/格式化字符串` 目录下的 writeup 和 exploit 示例，蒸馏一条训练样本：总结题目、漏洞点、利用链、关键代码和验证状态。",
"role": "user"
},
{
"content": "## 题目路径\n`其它漏洞/格式化字符串`\... | {
"category": "misc_vuln",
"ctf_score": 28,
"ctf_task_type": "ai",
"original_id": "pwn101-pair-c13186b93a7a9aa8",
"original_line": 497,
"original_split": "train",
"record_type": "writeup_exploit_pair",
"source_dataset": "pwn101_distilled_v1",
"source_path": "其它漏洞/格式化字符串",
"split": "train",
"split_... | pwn101_distilled_v1 | 其它漏洞/格式化字符串 | train | ctf_lora_sft |
misc_pwn | ai | ctf-dataset | ctf-lora-aa508a04c3bfd4f6167c | [
{
"content": "你是 CTF pwn、Linux kernel exploit 与二进制安全训练数据蒸馏助手。回答必须基于给定本地材料，保留关键路径、函数名、偏移、保护信息、利用原语和验证状态；不要编造材料中没有出现的事实。",
"role": "system"
},
{
"content": "根据 `其它/2024das usersys` 目录下的 writeup 和 exploit 示例，蒸馏一条训练样本：总结题目、漏洞点、利用链、关键代码和验证状态。",
"role": "user"
},
{
"content": "## 题目路径\n`其它/202... | {
"category": "misc_pwn",
"ctf_score": 24,
"ctf_task_type": "ai",
"original_id": "pwn101-pair-ce858bef636a2d76",
"original_line": 436,
"original_split": "train",
"record_type": "writeup_exploit_pair",
"source_dataset": "pwn101_distilled_v1",
"source_path": "其它/2024das usersys",
"split": "train",
"... | pwn101_distilled_v1 | 其它/2024das usersys | train | ctf_lora_sft |
misc_pwn | ai | ctf-dataset | ctf-lora-f7e1fcfe6f1fd3451842 | [
{
"content": "你是 CTF pwn、Linux kernel exploit 与二进制安全训练数据蒸馏助手。回答必须基于给定本地材料，保留关键路径、函数名、偏移、保护信息、利用原语和验证状态；不要编造材料中没有出现的事实。",
"role": "system"
},
{
"content": "根据 `其它/minishell` 目录下的 writeup 和 exploit 示例，蒸馏一条训练样本：总结题目、漏洞点、利用链、关键代码和验证状态。",
"role": "user"
},
{
"content": "## 题目路径\n`其它/minishell... | {
"category": "misc_pwn",
"ctf_score": 24,
"ctf_task_type": "ai",
"original_id": "pwn101-pair-ddcf33abeb0b3a15",
"original_line": 438,
"original_split": "train",
"record_type": "writeup_exploit_pair",
"source_dataset": "pwn101_distilled_v1",
"source_path": "其它/minishell",
"split": "train",
"split_... | pwn101_distilled_v1 | 其它/minishell | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-036b6b9fadec470a74a2 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/storage.md` 中的章节「值类型」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockchain... | {
"category": "blockchain",
"chars": 841,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "值类型",
"heading_path": [
"插槽式数组存储",
"值类型"
],
"original_id": "docs-e6fc27bdf8bdfb19e0f9",
"original_line": 153,
"original_split": "train",
"record_typ... | docs_distilled_v1 | blockchain/ethereum/storage.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-0440efb72e7a4eac0063 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/shortaddress.md` 中的章节「例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`doc... | {
"category": "blockchain",
"chars": 1862,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "例子",
"heading_path": [
"Short Address Attack",
"例子"
],
"original_id": "docs-1ddc025435690a0e3553",
"original_line": 10,
"original_split": "test",
"... | docs_distilled_v1 | blockchain/ethereum/attacks/shortaddress.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-08483a30c61c7f095101 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/basics.md` 中的章节「Interact with Contracts」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "... | {
"category": "blockchain",
"chars": 2674,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "Interact with Contracts",
"heading_path": [
"Ethereum Basics",
"Interact with Contracts"
],
"original_id": "docs-22baec519d02dec6f143",
"original_line"... | docs_distilled_v1 | blockchain/ethereum/basics.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-0a2076fb75790347be61 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/storage.md` 中的章节「FailedAttempt」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/... | {
"category": "blockchain",
"chars": 840,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "FailedAttempt",
"heading_path": [
"FailedAttempt"
],
"original_id": "docs-4af332e057c1c1da6d31",
"original_line": 159,
"original_split": "train",
"recor... | docs_distilled_v1 | blockchain/ethereum/storage.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-1789a7b8998f63983f76 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/overflow-underflow.md` 中的章节「例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来... | {
"category": "blockchain",
"chars": 1522,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "例子",
"heading_path": [
"Integer Overflow and Underflow",
"例子"
],
"original_id": "docs-581ea6d810ba52a0d554",
"original_line": 177,
"original_split": ... | docs_distilled_v1 | blockchain/ethereum/attacks/overflow-underflow.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-179039230a095dfd8c13 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/arbitrarywrite.md` 中的章节「Analyse」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "... | {
"category": "blockchain",
"chars": 1241,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "Analyse",
"heading_path": [
"Arbitrary Writing",
"例子",
"Analyse"
],
"original_id": "docs-6ae99e41803026d20268",
"original_line": 9,
"original_spl... | docs_distilled_v1 | blockchain/ethereum/attacks/arbitrarywrite.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-1947bded464f6bf8919d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/create2.md` 中的章节「例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blo... | {
"category": "blockchain",
"chars": 1936,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 25,
"ctf_task_type": "blockchain",
"heading": "例子",
"heading_path": [
"CREATE2",
"例子"
],
"original_id": "docs-5e066cb37561bfea9d03",
"original_line": 168,
"original_split": "train",
"record_type... | docs_distilled_v1 | blockchain/ethereum/attacks/create2.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-199a4ab1e94be3dcded2 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/delegatecall.md` 中的章节「Delegatecall」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content"... | {
"category": "blockchain",
"chars": 271,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "Delegatecall",
"heading_path": [
"Delegatecall"
],
"original_id": "docs-96ecdf9472c7d90aa9f0",
"original_line": 10,
"original_split": "validation",
"rec... | docs_distilled_v1 | blockchain/ethereum/attacks/delegatecall.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-1c048595fe155ec8b0f9 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/storage.md` 中的章节「插槽式数组存储」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockc... | {
"category": "blockchain",
"chars": 489,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "插槽式数组存储",
"heading_path": [
"插槽式数组存储"
],
"original_id": "docs-3b35e4026b765b3ed676",
"original_line": 152,
"original_split": "train",
"record_type": "do... | docs_distilled_v1 | blockchain/ethereum/storage.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-1d73ad366fc6bfcbeb89 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/storage.md` 中的章节「动态数组」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockchai... | {
"category": "blockchain",
"chars": 848,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "动态数组",
"heading_path": [
"插槽式数组存储",
"动态数组"
],
"original_id": "docs-f714c4fa6a9fc4cfef71",
"original_line": 155,
"original_split": "train",
"record_t... | docs_distilled_v1 | blockchain/ethereum/storage.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-1fa98068feb8bdbd4b81 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/resources.md` 中的章节「Static and Dynamic Analysis」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"cont... | {
"category": "blockchain",
"chars": 2089,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "Static and Dynamic Analysis",
"heading_path": [
"学习资源",
"Security Tools",
"Static and Dynamic Analysis"
],
"original_id": "docs-78ffb80677cc4bd30bcd"... | docs_distilled_v1 | blockchain/ethereum/resources.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-29ee64b70116eadd47eb | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/storage.md` 中的章节「例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockchain/... | {
"category": "blockchain",
"chars": 933,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 23,
"ctf_task_type": "blockchain",
"heading": "例子",
"heading_path": [
"插槽式数组存储",
"例子"
],
"original_id": "docs-d8797eb24e139f304d1e",
"original_line": 157,
"original_split": "train",
"record_type"... | docs_distilled_v1 | blockchain/ethereum/storage.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-2c41b8258bb2c80201a1 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/resources.md` 中的章节「Linters and Formatters」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "blockchain",
"chars": 504,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "Linters and Formatters",
"heading_path": [
"学习资源",
"Security Tools",
"Linters and Formatters"
],
"original_id": "docs-a6c4eac01d5144b1b272",
"origin... | docs_distilled_v1 | blockchain/ethereum/resources.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-3c569fa6b444a6438520 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/selector-encoding.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/b... | {
"category": "blockchain",
"chars": 385,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "原理",
"heading_path": [
"Function Selector and Argument Encoding",
"Function Selector",
"原理"
],
"original_id": "docs-ce50f11bc6459bfbc9d4",
"original... | docs_distilled_v1 | blockchain/ethereum/selector-encoding.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-42dc8166731392adc4de | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/arbitrarywrite.md` 中的章节「Map 映射变量」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": ... | {
"category": "blockchain",
"chars": 206,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "Map 映射变量",
"heading_path": [
"Arbitrary Writing",
"原理",
"slot 计算规则",
"Map 映射变量"
],
"original_id": "docs-0ddfd80434ab3a8fc1f0",
"original_line": ... | docs_distilled_v1 | blockchain/ethereum/attacks/arbitrarywrite.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-43d6298a444205f21050 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/resources.md` 中的章节「papers」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/block... | {
"category": "blockchain",
"chars": 267,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "papers",
"heading_path": [
"学习资源",
"papers"
],
"original_id": "docs-56f139fec3d42f0f6dcc",
"original_line": 139,
"original_split": "train",
"record_... | docs_distilled_v1 | blockchain/ethereum/resources.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-4d41a60d189f51a1d711 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/introduction.md` 中的章节「定义」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockc... | {
"category": "blockchain",
"chars": 515,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "定义",
"heading_path": [
"Ethereum Overview",
"定义"
],
"original_id": "docs-45002df6523e5f032d6a",
"original_line": 137,
"original_split": "train",
"re... | docs_distilled_v1 | blockchain/ethereum/introduction.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-4f00c225a0e103ec1c90 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/randomness.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/... | {
"category": "blockchain",
"chars": 294,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "原理",
"heading_path": [
"Randomness",
"使用 Blockhash 的伪随机数",
"原理"
],
"original_id": "docs-e4f64c774473cf8ac551",
"original_line": 181,
"original_spl... | docs_distilled_v1 | blockchain/ethereum/attacks/randomness.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-50cb8837812c17ca08f3 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/arbitrarywrite.md` 中的章节「变长数组」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：... | {
"category": "blockchain",
"chars": 347,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "变长数组",
"heading_path": [
"Arbitrary Writing",
"原理",
"slot 计算规则",
"变长数组"
],
"original_id": "docs-add4060b27b8ce15b4e6",
"original_line": 164,
"... | docs_distilled_v1 | blockchain/ethereum/attacks/arbitrarywrite.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-5aa7671482fecce26633 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/create2.md` 中的章节「CREATE」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs... | {
"category": "blockchain",
"chars": 249,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "CREATE",
"heading_path": [
"CREATE2",
"原理",
"CREATE"
],
"original_id": "docs-f421259a28ba4e8bf80a",
"original_line": 166,
"original_split": "train... | docs_distilled_v1 | blockchain/ethereum/attacks/create2.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-5c7f2f9e47819eb46158 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/opcodes.md` 中的章节「Ethereum Opcodes」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`do... | {
"category": "blockchain",
"chars": 1106,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "Ethereum Opcodes",
"heading_path": [
"Ethereum Opcodes"
],
"original_id": "docs-11a3a988245f5ed84cf1",
"original_line": 8,
"original_split": "test",
"r... | docs_distilled_v1 | blockchain/ethereum/opcodes.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-63e8e4a4dfdefb2f3ed6 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/selector-encoding.md` 中的章节「例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/b... | {
"category": "blockchain",
"chars": 933,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "例子",
"heading_path": [
"Function Selector and Argument Encoding",
"Function Selector",
"例子"
],
"original_id": "docs-953abffb4156e1b95aa7",
"original... | docs_distilled_v1 | blockchain/ethereum/selector-encoding.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-6bef0716b3cedd3a6e60 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/storage.md` 中的章节「SafeBox」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockc... | {
"category": "blockchain",
"chars": 230,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "SafeBox",
"heading_path": [
"SafeBox"
],
"original_id": "docs-993bf8712e07ada49d6c",
"original_line": 158,
"original_split": "train",
"record_type": "do... | docs_distilled_v1 | blockchain/ethereum/storage.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-7055d63c565e7ff4bf16 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/uninitialized-storage-pointer.md` 中的章节「典型例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
... | {
"category": "blockchain",
"chars": 2450,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "典型例子",
"heading_path": [
"Uninitialized Storage Pointer",
"例子",
"典型例子"
],
"original_id": "docs-48bc33c24ec558870d7e",
"original_line": 185,
"orig... | docs_distilled_v1 | blockchain/ethereum/attacks/uninitialized-storage-pointer.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-716fcff3b3f7fefffe05 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/arbitrarywrite.md` 中的章节「Source」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来... | {
"category": "blockchain",
"chars": 460,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 21,
"ctf_task_type": "blockchain",
"heading": "Source",
"heading_path": [
"Arbitrary Writing",
"例子",
"Source"
],
"original_id": "docs-739c35c1de208a642efe",
"original_line": 165,
"original_spli... | docs_distilled_v1 | blockchain/ethereum/attacks/arbitrarywrite.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-723120f44424a64771a1 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/selector-encoding.md` 中的章节「Function Selector and Argument Encoding」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user... | {
"category": "blockchain",
"chars": 287,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "Function Selector and Argument Encoding",
"heading_path": [
"Function Selector and Argument Encoding"
],
"original_id": "docs-d135a56cce9666dfd8aa",
"origin... | docs_distilled_v1 | blockchain/ethereum/selector-encoding.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-7a9525b53c615668de95 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/basics.md` 中的章节「合约账户」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockchain... | {
"category": "blockchain",
"chars": 833,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "合约账户",
"heading_path": [
"Ethereum Basics",
"账户",
"合约账户"
],
"original_id": "docs-a31fe882c59cd3ec61ff",
"original_line": 131,
"original_split": "t... | docs_distilled_v1 | blockchain/ethereum/basics.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-7cfe1c902e04786d32f6 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/attacks/randomness.md` 中的章节「例子」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/... | {
"category": "blockchain",
"chars": 1321,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 23,
"ctf_task_type": "blockchain",
"heading": "例子",
"heading_path": [
"Randomness",
"回滚攻击",
"例子"
],
"original_id": "docs-a39b4599d5e27d8b90e7",
"original_line": 182,
"original_split": "train",... | docs_distilled_v1 | blockchain/ethereum/attacks/randomness.md | train | ctf_lora_sft |
blockchain | blockchain | ctf-dataset | ctf-lora-7fe6d61d06ae43c33175 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/ethereum/basics.md` 中的章节「交易内容」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/blockchain... | {
"category": "blockchain",
"chars": 1286,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 19,
"ctf_task_type": "blockchain",
"heading": "交易内容",
"heading_path": [
"Ethereum Basics",
"交易",
"交易内容"
],
"original_id": "docs-0999f930629fbb04646e",
"original_line": 134,
"original_split": "... | docs_distilled_v1 | blockchain/ethereum/basics.md | train | ctf_lora_sft |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.