#

harmbench

Here are 3 public repositories matching this topic...

francordel / myrtia

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, chairman synthesis), 13 attack strategies, live turn-by-turn UI and ASR analytics. Open-source, built on IBM ARES.

Updated Oct 17, 2026
Python

Taleef7 / adaptation-not-algorithm

Code and data for "Adaptation, Not Algorithm" (Findings of AACL-IJCNLP 2026): LoRA vs. full fine-tuning and jailbreak safety in five open-weight LLMs

nlp jailbreak lora ai-safety fine-tuning peft red-teaming human-annotation aacl large-language-models qlora llm-evaluation llm-finetuning llm-safety llm-as-a-judge llm-jailbreaks harmbench jailbreakbench

Updated Oct 6, 2026
Python

austinmcclarin / injected-intelligence-llm-red-teaming

LLM red-teaming research using HarmBench to compare DirectRequest attack success rates across Llama 2, Vicuna, and Mistral.

python machine-learning cybersecurity red-teaming ai-security llm-security harmbench

Updated Aug 17, 2026
Python

Add this topic to your repo

To associate your repository with the harmbench topic, visit your repo's landing page and select "manage topics."