Techniquecommand-and-controlATLAS

AML.T0096AI Service API

What it is

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 [\[1\]][1]. [1]: https://www.microsoft.com/en-us/security/blog/2025/11/03/sesameop-novel-backdoor-uses-openai-assistants-api-for-command-and-control/

References

  1. https://atlas.mitre.org/techniques/AML.T0096

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

ATLAS
AI Agent
ATLAS
Data from AI Services
ATLAS
AI Model Inference API Access
ATLAS tactic
Command and Control
ATLAS
AI Agent Tool Invocation
ATLAS tactic
AI Model Access
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.