Label-only membership inference attack based on the transferability of adversarial sample

Xiaowei Hao; Dong Zhang; Hanwei Wu; Jing Duan; Long An; Xiu Liu

doi:10.1117/12.2640751

13 October 2022 Label-only membership inference attack based on the transferability of adversarial sample

Xiaowei Hao, Dong Zhang, Hanwei Wu, Jing Duan, Long An, Xiu Liu

Proceedings Volume 12287, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022); 122870D (2022) https://doi.org/10.1117/12.2640751
Event: International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022), 2022, Wuhan, China

Abstract

Machine learning (ML) has been widely used in various scenes, such as face recognition, automatic driving and image recognition and other fields. However, in these applications, attackers usually exploit various vulnerabilities in machine learning models to mine private information, including model training information and private data information. The attacks against machine learning training data mainly include membership inference attack (MIA). The attacker of membership inference attack will judge whether the data sample is in the training data set of the target model given the data sample and the target model. Most of the existing member inference attacks are based on confidence attacks. Researchers found that if the confidence returned is hidden, they can effectively defend against these attacks. Therefore, the latest research proposed label-only attack, but this attack requires hundreds of queries for a sample, and abnormal query accesses are easy to be found by the target model. In this paper, we propose a member inference attack based on the transferability of adversarial samples. The adversarial samples generated under different models of the same task have certain mobility characteristics, so as to use the shadow model to generate adversarial samples for attack and reduce the attack cost. The evaluation shows that under the restriction of fewer queries, only the label output will still reveal private information, and the performance of the member inference attack based on the transferability of adversarial samples is better than that based on confidence in most cases.

Citation Download Citation

Xiaowei Hao, Dong Zhang, Hanwei Wu, Jing Duan, Long An, and Xiu Liu "Label-only membership inference attack based on the transferability of adversarial sample", Proc. SPIE 12287, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022), 122870D (13 October 2022); https://doi.org/10.1117/12.2640751

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Statistical modeling

Machine learning

Binary data

Defense and security

Distance measurement

Facial recognition systems

Show All Keywords

Keywords/Phrases

Search In:

Publication Years