During a security audit, security analysts discover that an attacker has been repeatedly querying a...

A membership inference attack is when an attacker determines whether specific data was used in the training set of a machine learning model by analyzing the model’s responses to queries. This is a major privacy threat for AI and ML systems, as referenced in information security and privacy controls for machine learning.

“Membership inference attacks allow adversaries to determine if certain records were part of the model’s training data, which can lead to privacy violations.”

— NIST SP 800-53 Rev. 5, ISO/IEC 27001:2022, Annex A 8.19