SubTechniqueexfiltrationATLAS

AML.T0024.000Infer Training Data Membership

What it is

Adversaries may infer the membership of a data sample or global characteristics of the data in its training set, which raises privacy concerns. Some strategies make use of a shadow model that could be obtained via [Train Proxy via Replication](/techniques/AML.T0005.001), others use statistics of model prediction scores. This can cause the victim model to leak private information, such as PII of those in the training set or other forms of protected IP.

References

  1. https://atlas.mitre.org/techniques/AML.T0024.000

Related by meaning· 6

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

ATLAS
Exfiltration via AI Inference API
ATLAS
Poison Training Data
ATLAS
AI Model Inference API Access
ATLAS
Impersonation
ATLAS
LLM Data Leakage
ATLAS
Craft Adversarial Data
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.