ATLASAML.T0024.001
ATLAS index
AML.T0024.001

Invert AI Model

AI models' training data could be reconstructed by exploiting the confidence scores that are available via an inference API. By querying the inference API strategically, adversaries can back out potentially private information embedded within the training data. This could lead to privacy violations if the attacker can

Framework
MITRE ATLAS
Maturity
Feasible
Platforms
Predictive AI, Generative AI, Agentic AI
Release
2026.05

Overview

AI models' training data could be reconstructed by exploiting the confidence scores that are available via an inference API. By querying the inference API strategically, adversaries can back out potentially private information embedded within the training data. This could lead to privacy violations if the attacker can reconstruct the data of sensitive features used in the algorithm.

Sources

  1. MITRE ATLAS AML.T0024.001: Invert AI Model — MITRE