---
base_model: google/gemma-3-270m-it
library_name: peft
license: apache-2.0
tags:
  - cybersecurity
  - pentesting
  - active-directory
  - lora
  - openworlds
  - gemma-3
pipeline_tag: text-generation
datasets:
  - omkar6699/openworlds-ad-trajectories
---

# OpenWorlds Pentest Agent (Gemma 3 270M + LoRA)

A LoRA adapter fine-tuned on synthetic Active Directory penetration testing trajectories.

## Model Description

- **Base model:** google/gemma-3-270m-it
- **Fine-tuning:** LoRA (r=16, alpha=32)
- **Training data:** 20 trajectories from OpenWorlds
- **Objective:** Teach small LLMs to perform structured AD penetration testing

## Capabilities

The model learns to:
1. **Reason** about attack paths (<think> traces)
2. **Select** appropriate pentesting tools (nmap, GetUserSPNs, hashcat, etc.)
3. **Recover** from failures (wrong commands, typos, permission denied)
4. **Escalate** privileges from low-priv user to Domain Admin

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("google/gemma-3-270m-it")
model = PeftModel.from_pretrained(base, "omkar6699/openworlds-pentest-agent")
tokenizer = AutoTokenizer.from_pretrained("omkar6699/openworlds-pentest-agent")

prompt = "You are a penetration tester. Target domain: corp.local."
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(output[0]))
```

## Training

```bash
pip install openworlds[training]
openworlds manifest generate --hosts 10 --users 25 --seed 42
openworlds trajectory generate
openworlds train run --model google/gemma-3-270m-it --cpu --chat-format auto
```

## Limitations

- Trained on synthetic data (simulated tool outputs, not real networks)
- Small base model (270M) -- use as a starting point, scale up for production
- For authorized security testing and research only

## License

Apache 2.0