llm-safety topic

Attack to induce LLMs within hallucinations

PKU-YuanGroup

Restore safety in fine-tuned language models through task arithmetic

declare-lab

Papers about red teaming LLMs and Multimodal models.

Libr-AI

Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"

Babelscape

Code and dataset for the paper: "Can Editing LLMs Inject Harm?"

llm-editing

Comprehensive LLM testing suite for safety, performance, bias, and compliance, equipped with methodologies and tools to enhance the reliability and ethical integrity of models like OpenAI's GPT series...

copyleftdev

DeepTeam is a framework to red team LLMs and LLM systems.

confident-ai

[NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.

CryptoAILab