MITRE ATLAS · Defense Evasion
AML.T0134 · AI Targeted Cloaking
Adversaries may selectively deliver malicious or manipulated content to AI systems, while presenting different benign content to human users, web crawlers, or security detection mechanisms. They may identify AI browsers or agents via user-agent strings and condition the server response so that AI-based clients receive prompt injections or misleading content.
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.