Membership Inference Attack

An attack that determines whether a specific data record was part of a model's training dataset, potentially revealing sensitive information about individuals.

An attack where someone figures out if a specific person's data was used to train an AI. For example, determining that your medical records were part of a health AI's training data.

Understanding this attack vector is important for AI risk management. If your AI models are trained on sensitive data, your governance framework should include controls to prevent membership inference and protect individual privacy.