Techniquedefense-evasionATLAS
AML.T0076Corrupt AI Model
What it is
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.
References
Related by meaning· 6
Nearest entities by semantic similarity across the cs-graph corpus.