Common Information
Type Value
Value
Infer Training Data Membership
Category Attack-Pattern
Type Mitre-Atlas-Attack-Pattern
Misp Type Cluster
Description Adversaries may infer the membership of a data sample 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.
Details Published Attributes CTI Title
Details Website 2024-09-30 2 Threat-Informed Defense to Secure AI
Details Website 2024-09-16 0 Pentesting AI Applications-OWASP Top 10 for LLMs