An easy-to-use Python framework to generate adversarial jailbreak prompts.
Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"
[ICLR 2025] Official implementation for "SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations"
Restore safety in fine-tuned language models through task arithmetic
SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems
LiveSecBench，面向中文场景的大模型安全评测基准。框架结合动态题库、模型对战与客观评分流程，可在伦理、合法性、事实性、隐私、对抗鲁棒与推理安全等核心维度持续追踪模型表现。
Red-team framework for discovering alignment failures in frontier language models.
Add a description, image, and links to the llm-safety-benchmark topic page so that developers can more easily learn about it.
To associate your repository with the llm-safety-benchmark topic, visit your repo's landing page and select "manage topics."