MITRE ATLAS · Defense Evasion
AML.T0067 · LLM Trusted Output Components Manipulation
Adversaries may utilize prompts to a large language model (LLM) which manipulate various components of its response in order to make it appear trustworthy to the user. This helps the adversary continue to operate in the victim's environment and evade detection by the users it interacts with.
Mitigations
- Generative AI Guardrails
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.