MExMI: Pool-based Active Model Extraction Crossover Membership Inference

Yaxin Xiao, Qingqing Ye, Haibo Hu, Huadi Zheng, Chengfang Fang, Jie Shi

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)

Abstract

With increasing popularity of Machine Learning as a Service (MLaaS), ML models trained from public and proprietary data are deployed in the cloud and deliver prediction services to users. However, as the prediction API becomes a new attack surface, growing concerns have arisen on the confidentiality of ML models. Existing literatures show their vulnerability under model extraction (ME) attacks, while their private training data is vulnerable to another type of attacks, namely, membership inference (MI). In this paper, we show that ME and MI can reinforce each other through a chained and iterative reaction, which can significantly boost ME attack accuracy and improve MI by saving the query cost. As such, we build a framework MExMI for pool-based active model extraction (PAME) to exploit MI through three modules: “MI Pre-Filter”, “MI Post-Filter”, and “semi-supervised boosting”. Experimental results show that MExMI can improve up to 11.14% from the best known PAME attack and reach 94.07% fidelity with only 16k queries. Furthermore, the accuracy, precision and recall of the MI attack in MExMI are on par with state-of-the-art MI attack which needs 150k queries.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
EditorsS. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
PublisherNeural information processing systems foundation
Pages1-14
ISBN (Electronic)9781713871088
Publication statusPublished - Dec 2022
Event36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans, United States
Duration: 28 Nov 20229 Dec 2022

Publication series

NameAdvances in Neural Information Processing Systems
Volume35
ISSN (Print)1049-5258

Conference

Conference36th Conference on Neural Information Processing Systems, NeurIPS 2022
Country/TerritoryUnited States
CityNew Orleans
Period28/11/229/12/22

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'MExMI: Pool-based Active Model Extraction Crossover Membership Inference'. Together they form a unique fingerprint.

Cite this