閱讀 MITRE ATLAS 中 AML.T0076「Corrupt AI Model」相關的 1 個 AI 資安案例,查看事件證據、適用範圍與 AIDEFEND 防禦分析。
風險分類說明
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.