AlphaUncommon
AI-secure/AgentPoison
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
- Owner
- AI-secure (organization)
- Stars
- Stars: 250
- Forks
- Forks: 35
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- llm-agentred-teamretrieval-augmented-generation
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by AI-secure
All 4 repos by AI-secure- AI-secure/DecodingTrustStars: 318PythonAlpha
- AI-secure/DBAStars: 206PythonPrototype
- AI-secure/DecodingTrust-Agent-PlatformStars: 100PythonPrototype
Nearby in Python
All Python repos- molence/Mol-1Stars: 250PythonAlpha
- MUSE-AI-Lab/SurveyGraphStars: 250PythonAlpha
- didi/helixharnessStars: 250PythonAlpha
- alex/django-ajax-validationStars: 250PythonAlpha
- Cue/fast-python-pbStars: 250PythonAlpha
- opendataphilly/Open-Data-CatalogStars: 250PythonAlpha