Threat intelligence / Technique
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.
Technique
TypeTechnique
External ID—
First seen2026-08-14
Last seen2026-08-14
Confidence
—
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.
1 recorded
Relationships
1 external