On the Vulnerability of Data Points Under Multiple Membership Inference Attacks and Target Models
Mauro Conti (Università degli Studi di Padova, TU Delft - Cyber Security, University of Washington)
Jiaxin Li (Università degli Studi di Padova)
Stjepan Picek (Radboud Universiteit Nijmegen)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model, posing privacy risks to sensitive data like medical records or financial data. Intuitively, data points that MIA accurately detects are vulnerable. Those data points may exist in the data of different target models, each susceptible to multiple MIAs. As such, the vulnerability of data points under multiple MIAs and target models represents a significant challenge. This article defines several metrics reflecting data points’ vulnerability and capturing vulnerable data points under multiple MIAs and target models. We implement 77 MIAs, with an average attack accuracy over target models ranging from 0.5 to 0.9, to support our analysis with our scalable and flexible platform, Various Membership Inference Attacks Platform (VMIAP). Based on the results, we observe that MIA has an inference tendency to some data points despite a low overall inference performance. Furthermore, previous approaches are unsuitable for finding vulnerable data points under multiple MIAs and target models. Finally, we explore the impact of retraining target, shadow, and attack models separately on the vulnerability of data points.