PECB
LEAD-IMPLEMENTER · Question #201
During a security audit, analysts discover that an attacker repeatedly queried a black-box ML model to infer if specific data points were in the training set. The attacker could determine if an…
The correct answer is C. Membership inference attack. See the full explanation below for the reasoning.
Question
During a security audit, analysts discover that an attacker repeatedly queried a black-box ML model to infer if specific data points were in the training set. The attacker could determine if an individual's data was used during training. What threat does this attack represent?
Options
- ABackdoor in the training set
- BData poisoning
- CMembership inference attack
How the community answered
(28 responses)- A7% (2)
- B14% (4)
- C79% (22)
Community Discussion
No community discussion yet for this question.