Ahmed Salem (CISPA Helmholtz Center for Information Security), Yang Zhang (CISPA Helmholtz Center for Information Security), Mathias Humbert (Swiss Data Science Center, ETH Zurich/EPFL), Pascal Berrang (CISPA Helmholtz Center for Information Security), Mario Fritz (CISPA Helmholtz Center for Information Security), Michael Backes (CISPA Helmholtz Center for Information Security)

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS). Recently, the first membership inference attack has shown that extraction of information on the training set is possible in such MLaaS settings, which has severe security and privacy implications.

However, the early demonstrations of the feasibility of such attacks have many assumptions on the adversary, such as using multiple so-called shadow models, knowledge of the target model structure, and having a dataset from the same distribution as the target model's training data. We relax all these key assumptions, thereby showing that such attacks are very broadly applicable at low cost and thereby pose a more severe risk than previously thought. We present the most comprehensive study so far on this emerging and developing threat using eight diverse datasets which show the viability of the proposed attacks across domains.

In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.

View More Papers

TIMBER-V: Tag-Isolated Memory Bringing Fine-grained Enclaves to RISC-V

Samuel Weiser (Graz University of Technology), Mario Werner (Graz University of Technology), Ferdinand Brasser (Technische Universität Darmstadt), Maja Malenko (Graz University of Technology), Stefan Mangard (Graz University of Technology), Ahmad-Reza Sadeghi (Technische Universität Darmstadt)

Read More

IoTGuard: Dynamic Enforcement of Security and Safety Policy in...

Z. Berkay Celik (Penn State University), Gang Tan (Penn State University), Patrick McDaniel (Penn State University)

Read More

Cracking the Wall of Confinement: Understanding and Analyzing Malicious...

Eihal Alowaisheq (Indiana University, King Saud University), Peng Wang (Indiana University), Sumayah Alrwais (King Saud University), Xiaojing Liao (Indiana University), XiaoFeng Wang (Indiana University), Tasneem Alowaisheq (Indiana University, King Saud University), Xianghang Mi (Indiana University), Siyuan Tang (Indiana University), Baojun Liu (Tsinghua University)

Read More

CRCount: Pointer Invalidation with Reference Counting to Mitigate Use-after-free...

Jangseop Shin (Seoul National University and Inter-University Semiconductor Research Center), Donghyun Kwon (Seoul National University and Inter-University Semiconductor Research Center), Jiwon Seo (Seoul National University and Inter-University Semiconductor Research Center), Yeongpil Cho (Soongsil University), Yunheung Paek (Seoul National University and Inter-University Semiconductor Research Center)

Read More