Litcius/Paper detail

Practical Blind Membership Inference Attack via Differential Comparisons

Bo Hui, Yuchen Yang, Haolin Yuan, Philippe Burlina, Neil Zhenqiang Gong, Yinzhi Cao

202182 citationsDOIOpen Access PDF

Abstract

Membership inference (MI) attacks affect user privacy by inferring whether given data samples have been used to train a target learning model, e.g., a deep neural network. There are two types of MI attacks in the literature, i.e., these with and without shadow models. The success of the former heavily depends on the quality of the shadow model, i.e., the transferability between the shadow and the target; the latter, given only blackbox probing access to the target model, cannot make an effective inference of unknowns, compared with MI attacks using shadow models, due to the insufficient number of qualified samples labeled with ground truth membership information.

Topics & Concepts

Computer scienceInferenceShadow (psychology)Set (abstract data type)Artificial intelligenceDifferential (mechanical device)Ground truthDifferential privacySample (material)Data miningAdversaryMachine learningPattern recognition (psychology)Computer securityEngineeringProgramming languageChromatographyPsychotherapistAerospace engineeringChemistryPsychologyPrivacy-Preserving Technologies in DataAdversarial Robustness in Machine LearningForensic and Genetic Research
Practical Blind Membership Inference Attack via Differential Comparisons | Litcius