| experiment: | |
| name: hackaprompt_override_25_gpt_oss_20b | |
| description: HackAPrompt instruction-override pressure test (baseline, gpt_oss_20b) | |
| seed: 42 | |
| sample_size: 25 | |
| output_dir: results | |
| dataset: | |
| path: data/normalized/attack_cases.jsonl | |
| selection: | |
| include_sources: | |
| - HackAPrompt | |
| include_attack_families: | |
| - direct_instruction_override | |
| - compound_instruction_attack | |
| - sandwich_defense_bypass | |
| require_expected_target: true | |
| model: | |
| provider: groq | |
| name: openai/gpt-oss-20b | |
| max_tokens: 256 | |
| temperature: 0.0 | |
| execution_mode: attack_then_task | |
| mitigation: | |
| enabled: false | |
| strategy: none | |
| evaluation: | |
| metrics: | |
| - attack_success | |