AML.T0076
Corrupt AI Model
An adversary may purposefully corrupt a malicious AI model file so that it cannot be successfully deserialized in order to evade detection by a model scanner. The corrupt model may still successfully execute malicious code before deserialization fails.
- Tactic Defense Evasion
- Maturity: Realized
- Predictive AI
- Generative AI
- Agentic AI
Mitigations
ATLAS lists no mitigation for this technique yet.
From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.