# centerforaisafety/harmbench

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/centerforaisafety-harmbench).**

991 stars · 145 forks · Jupyter Notebook · MIT

## Links

- GitHub: https://github.com/centerforaisafety/HarmBench
- Homepage: https://harmbench.org
- awesome-repositories: https://awesome-repositories.com/repository/centerforaisafety-harmbench.md

## Description

📰 Latest News 📰 - 🗡️ What is HarmBench 🛡️ - 🌐 Overview 🌐 - ☕ Quick Start ☕ - ⚙️ Installation - 🛠️ Running the Evaluation Pipeline - ➕ Using your own models in HarmBench - ➕ Using your own red teaming methods in HarmBench - 🤗 Classifiers - ⚓ Documentation ⚓ - 🌱 HarmBench's Roadmap 🌱 -…

## Tags

### Part of an Awesome List

- [Evaluation Benchmarks](https://awesome-repositories.com/f/awesome-lists/ai/evaluation-benchmarks.md) — Standardized framework for automated red teaming and refusal.
- [Guardrails and AI Safety](https://awesome-repositories.com/f/awesome-lists/more/guardrails-and-ai-safety.md) — Listed in the “Guardrails and AI Safety” section of the The Incredible Pytorch awesome list.