Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Hongyao, Qiu, Yixiang, Fang, Hao, Zhuang, Tianqu, Chen, Bin, Yu, Sijin, Wang, Bin, Xia, Shu-Tao, Xu, Ke
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917116642328576
author Yu, Hongyao
Qiu, Yixiang
Fang, Hao
Zhuang, Tianqu
Chen, Bin
Yu, Sijin
Wang, Bin
Xia, Shu-Tao
Xu, Ke
author_facet Yu, Hongyao
Qiu, Yixiang
Fang, Hao
Zhuang, Tianqu
Chen, Bin
Yu, Sijin
Wang, Bin
Xia, Shu-Tao
Xu, Ke
contents Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of MIAs across diverse settings, defense strategies have lagged behind, struggling to balance model utility with robustness against increasingly sophisticated attacks. In this work, we propose the ideal inversion error to measure the privacy leakage, and our theoretical and empirical investigations reveals that higher-rank features are inherently more prone to privacy leakage. Motivated by this insight, we propose a lightweight and effective defense strategy based on low-rank feature filtering, which explicitly reduces the attack surface by constraining the dimension of intermediate representations. Extensive experiments across various model architectures and datasets demonstrate that our method consistently outperforms existing defenses, achieving state-of-the-art performance against a wide range of MIAs. Notably, our approach remains effective even in challenging regimes involving high-resolution data and high-capacity models, where prior defenses fail to provide adequate protection. The code is available at https://github.com/Chrisqcwx/LoFt .
format Preprint
id arxiv_https___arxiv_org_abs_2410_05814
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
Yu, Hongyao
Qiu, Yixiang
Fang, Hao
Zhuang, Tianqu
Chen, Bin
Yu, Sijin
Wang, Bin
Xia, Shu-Tao
Xu, Ke
Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of MIAs across diverse settings, defense strategies have lagged behind, struggling to balance model utility with robustness against increasingly sophisticated attacks. In this work, we propose the ideal inversion error to measure the privacy leakage, and our theoretical and empirical investigations reveals that higher-rank features are inherently more prone to privacy leakage. Motivated by this insight, we propose a lightweight and effective defense strategy based on low-rank feature filtering, which explicitly reduces the attack surface by constraining the dimension of intermediate representations. Extensive experiments across various model architectures and datasets demonstrate that our method consistently outperforms existing defenses, achieving state-of-the-art performance against a wide range of MIAs. Notably, our approach remains effective even in challenging regimes involving high-resolution data and high-capacity models, where prior defenses fail to provide adequate protection. The code is available at https://github.com/Chrisqcwx/LoFt .
title Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
topic Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2410.05814