GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation

no code implementations • 13 May 2024 • Andrey V. Galichin, Mikhail Pautov, Alexey Zhavoronkin, Oleg Y. Rogov, Ivan Oseledets

We observe that the knowledge distillation significantly improves the efficiency of likelihood ratio of membership inference attack, especially in the black-box setting, i. e., when the architecture of the target model is unknown to the attacker.

Image Classification Inference Attack +2