MITRE ATLAS · Persistence
AML.T0070 · RAG Poisoning
Adversaries may inject malicious content into data indexed by a retrieval augmented generation (RAG) system to contaminate a future thread through RAG-based search results. This may be accomplished by placing manipulated documents in a location the RAG indexes (see Gather RAG-Indexed Targets).
Mitigations
- Generative AI Guardrails
- AI Red Team
Related techniques
- LLM08 Vector and Embedding Weaknesses OWASP LLM
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.