Uncensored and Offensive Security AI Models Benchmark
This article presents a curated benchmark list of open-weight, uncensored AI models specifically designed for authorized red team operations, penetration testing, and security research. It details several models like DeepHat V2 and BugTraceAI-CORE-Apex, outlining their base models, parameters, context length, VRAM requirements, uncensoring methods, training data, and licenses.
Why it matters
The development and benchmarking of uncensored AI models for cybersecurity purposes highlight a growing trend in leveraging advanced AI for both offensive and defensive security operations, raising questions about ethical use and the dual-nature of such powerful tools.
Curated list of open-weight uncensored models for authorized red team operations, penetration testing, and security research.
All data sourced from HuggingFace model cards and official publications. Sep 2026.
1. DeepHat V2 (WhiteRabbitNeo) Spec Value Base Model Qwen2.5-Coder-7B Parameters 7B / 32B Context Length 131K VRAM (Q4_K_M) ~6 GB Uncensoring Method SFT on 1.7M offensive/defensive samples Training Data 1.7M security-specific samples (USENIX Security 2024 workshop) Vision No Tool Calling Yes License Apache 2.0 Download: https://huggingface.co/WhiteRabbitNeo
Spec Value Base Model Gemma4-26B MoE Parameters 26B MoE Context Length 32K VRAM (Q4_K_M) ~16 GB Uncensoring Method SFT on HackerOne Hacktivity 2024-2025 Training Data HackerOne reports + WAF evasion dataset Vision No Tool Calling Yes License Apache 2.0 Download: https://huggingface.co/BugTraceAI/BugTraceAI-CORE-Apex-26b
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in