Defenses to Membership Inference Attacks: A Survey

Machine learning (ML) has gained widespread adoption in a variety of fields, including computer vision and natural language processing. However, ML models are vulnerable to membership inference attacks (MIAs), which can infer whether access data was used in training a target model, thus compromising...

Full description

Saved in:
Bibliographic Details
Published in:ACM computing surveys 2024-04, Vol.56 (4), p.1-34, Article 92
Main Authors: Hu, Li, Yan, Anli, Yan, Hongyang, Li, Jin, Huang, Teng, Zhang, Yingying, Dong, Changyu, Yang, Chunsheng
Format: Article
Language:English
Subjects:
Computer science
Computer vision
Inference
Machine learning
Natural language processing
Privacy
Privacy protections
Security and privacy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning (ML) has gained widespread adoption in a variety of fields, including computer vision and natural language processing. However, ML models are vulnerable to membership inference attacks (MIAs), which can infer whether access data was used in training a target model, thus compromising the privacy of training data. This has led researchers to focus on protecting the privacy of ML. To date, although there have been extensive efforts to defend against MIAs, we still lack a comprehensive understanding of the progress made in this area, which can often impede our ability to design the most effective defense strategies. In this article, we aim to fill this critical knowledge gap by providing a systematic analysis of membership inference defense. Specifically, we classify and summarize the existing membership inference defense schemes, focusing on optimization phase and objective, basic intuition, and key technology, and we discuss possible research directions of membership inference defense in the future.
ISSN:0360-0300
1557-7341
DOI:10.1145/3620667