How to meet it
OWASP AISVS v1.01
Adversarial Robustness · Membership-Inference and Model-Inversion Mitigation
Test against membership inference
Verify that membership-inference attack simulations demonstrate that attack accuracy does not exceed random guessing on evaluated data.
OWASP AISVS v1.01, requirement 11.2.5
In plain English
Test whether an attacker could tell if a given record was in your training data. The attack should do no better than a random guess.
What good looks like
- Membership-inference attacks are simulated on the trained model.
- Results are compared with random guessing.
- Models that fail are not released.
How teams usually do it
- Open privacy testing tools that run standard membership-inference attacks.
Evidence an auditor would accept
- Attack simulation results.
Common mistakes
- Testing only on records the model handles well.
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.