AltaySec · ATLAS 2026.07
AML.T0076

Corrupt AI Model

C · Explainer (cannot be honestly simulated in-browser) AML.TA0007 · Defense Evasion

Description

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.

Honesty-tier rationale

This technique should be measured against a real defense stack; in-browser, only a simple filter-vs-filter illustration is honest.

Source

← Back to the matrix