Zitao Chen (University of British Columbia), Karthik Pattabiraman (University of British Columbia)

Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf codebase to build high-performance ML models on their data, many of which are sensitive in nature (e.g., clinical records).

In this work, we consider a malicious ML provider who supplies model-training code to the data holders, does not have access to the training process, and has only black-box query access to the resulting model. In this setting, we demonstrate a new form of membership inference attack that is strictly more powerful than prior art. Our attack empowers the adversary to reliably de-identify all the training samples (average >99% attack [email protected]% FPR), and the compromised models still maintain competitive performance as their uncorrupted counterparts (average <1% accuracy drop). Moreover, we show that the poisoned models can effectively disguise the amplified membership leakage under common membership privacy auditing, which can only be revealed by a set of secret samples known by the adversary. Overall, our study not only points to the worst-case membership privacy leakage, but also unveils a common pitfall underlying existing privacy auditing methods, which calls for future efforts to rethink the current practice of auditing membership privacy in machine learning models.

View More Papers

BinEnhance: An Enhancement Framework Based on External Environment Semantics...

Yongpan Wang (Institute of Information Engineering Chinese Academy of Sciences & University of Chinese Academy of Sciences, China), Hong Li (Institute of Information Engineering Chinese Academy of Sciences & University of Chinese Academy of Sciences, China), Xiaojie Zhu (King Abdullah University of Science and Technology, Thuwal, Saudi Arabia), Siyuan Li (Institute of Information Engineering Chinese…

Read More

BrowserFM: A Feature Model-based Approach to Browser Fingerprint Analysis

Maxime Huyghe (Univ. Lille, Inria, CNRS, UMR 9189 CRIStAL), Clément Quinton (Univ. Lille, Inria, CNRS, UMR 9189 CRIStAL), Walter Rudametkin (Univ. Rennes, Inria, CNRS, UMR 6074 IRISA)

Read More

Attributing Open-Source Contributions is Critical but Difficult: A Systematic...

Jan-Ulrich Holtgrave (CISPA Helmholtz Center for Information Security), Kay Friedrich (CISPA Helmholtz Center for Information Security), Fabian Fischer (CISPA Helmholtz Center for Information Security), Nicolas Huaman (Leibniz University Hannover), Niklas Busch (CISPA Helmholtz Center for Information Security), Jan H. Klemmer (CISPA Helmholtz Center for Information Security), Marcel Fourné (Paderborn University), Oliver Wiese (CISPA Helmholtz Center…

Read More

The Kids Are All Right: Investigating the Susceptibility of...

Elijah Bouma-Sims (Carnegie Mellon University), Lily Klucinec (Carnegie Mellon University), Mandy Lanyon (Carnegie Mellon University), Julie Downs (Carnegie Mellon University), Lorrie Faith Cranor (Carnegie Mellon University)

Read More