閱讀 MITRE ATLAS 中 AML.T0096「AI Service API」相關的 5 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 communicate using the API of an AI service on the victim's system. The adversary's commands to the victim system, and often the results, are embedded in the normal traffic of the AI service. An AI service API command and control channel is covert because the adversary's commands blend in with normal communications, so an adversary may use this technique to avoid detection. Using existing infrastructure on the victim's system allows the adversary to live off the land, further reducing their footprint. AI service APIs may be abused as C2 channels when an adversary wants to be stealthy and maintain long-term persistence for espionage activities [[microsoft]].
Microsoft Incident Response - Detection and Response Team(DART)在調查一起系統入侵事件時發現,攻擊者使用一支名為 SesameOp 的後門程式進行間諜活動。這支後門把 OpenAI Assistants API 當成隱蔽的命令與控制(C2)通道:它透過 OpenAI API 取得並執行攻擊者下達的命令,再把加密後的執行結果從受害主機傳回去。 攻擊者已經在這台被入侵的系統上潛伏數個月。他們控制了多個內部 web shell,這些 web shell 會執行來自惡意行程的命令,而那些行程依附在被竄改過的 Visual Studio 工具程式上。調查其他 Visual Studio 工具程式時,才發現了這支新型的 SesameOp 後門。