Techniquepersistenceai-attack-stagingATLAS

AML.T0018Manipulate AI Model

What it is

Adversaries may directly manipulate an AI model to change its behavior or introduce malicious code. Manipulating a model gives the adversary a persistent change in the system. This can include poisoning the model by changing its weights, modifying the model architecture to change its behavior, and embedding malware which may be executed when the model is loaded.

References

  1. https://atlas.mitre.org/techniques/AML.T0018

Related by meaning· 6

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

ATLAS
AI Agent Tool Poisoning
ATLAS
Modify AI Agent Configuration
ATLAS
Corrupt AI Model
ATLAS
Poison Training Data
ATLAS tactic
AI Model Access
ATLAS
Publish Poisoned Models
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.