MITRE ATLAS · Persistence
AML.T0145 · Poison AI Agent Learning Environment
Adversaries may manipulate an environment in which an AI agent interacts so that observations, feedback, rewards, actions, or resulting interactions are incorporated into model training to cause persistent changes to the behavior of an AI system. This allows adversary's influence to persist beyond the original interaction and affect subsequent tasks.
Mitigations
- Sanitize Training Data
- Validate AI Model
- Generative AI Guardrails
- Generative AI Model Alignment
- Maintain AI Dataset Provenance
- AI Red Team
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.