R_REDDYX.XYZ
AIPython★ 256⑂ 35 forksMIT

AI-secure/AgentPoison

AGENTPOISON: POISONING LLM AGENTS

The official NeurIPS 2024 implementation shows how to inject backdoors into the memory or knowledge base of LLM agents to test their robustness against attacks.

// KEY FEATURES

  • Backdoor injection via memory or knowledge base
  • Red team methods for evaluating LLM agents
  • Python support, ready for integration into research
#llm-agent#red-team#retrieval-augmented-generation
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Free 1688 Data Query★ 256WRITE DAX BY VOICE!★ 256MCP Fusion: Secure TypeScript★ 256BAIBOT: MATRIX BOT FOR AI★ 256MCP SERVER FOR NETBOX/LLM★ 256YOLOAI SECRET AI SANDBOX★ 256

← FULL CATALOG

AI-secure/AgentPoison — Agentpoison: Poisoning LLM Agents