Membership Inference (2f735ad0-22a9-5ae6-9151-77886408a028)
In a membership inference attack (MIA), the attacker can determine whether a given data record was part of the model’s training dataset or not. Example: researchers were able to predict a patient’s main procedure (e.g., surgery the patient went through) based on the attributes (e.g., age, gender, hospital).
Threat-modeling question: Are we protected from membership inference attacks?