The Eval Index / Red Teaming & Safety / #126

AI-secure/AgentPoison

by AI-secure · Red Teaming & Safety · updated 27d ago

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

56
momentum
243
stars
34
forks
#126
rank
llm-agentred-teamretrieval-augmented-generation
View on GitHub →