AML.T0013 · Discover AI Model Ontology

閱讀 MITRE ATLAS 中 AML.T0013「Discover AI Model Ontology」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

Adversaries may discover the ontology of an AI model's output space, for example, the types of objects a model can detect. The adversary may discover the ontology by repeated queries to the model, forcing it to enumerate its output space. Or the ontology may be discovered in a configuration file or in documentation about the model. The model ontology helps the adversary understand how the model is being used by the victim. It is useful to the adversary in creating targeted attacks.

框架官方來源 ↗ · 開啟互動探索 ↗

Exercise ·

以實體對抗物規避人臉辨識系統

MITRE 的 AI 紅隊對一項商用人臉辨識服務,示範了實體世界中的規避攻擊,目標是誘導出特定的錯誤辨識結果。這次行動同時用上了傳統的 MITRE ATT&CK 手法,例如找出可用的有效帳號、透過 API 執行程式碼,並在其中穿插了對抗式機器學習專屬的攻擊。

沿用 SecureFlow 來源步驟的 ATLAS 標註;不是 MITRE 對跨框架對應的背書。

SecureFlow · 閱讀完整案例 ↗