Chenxiang Luo (City University of Hong Kong), David K.Y. Yau (Singapore University of Technology and Design), Qun Song (City University of Hong Kong)

Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where adversaries reconstruct private data from shared gradients. Existing defenses either incur impractical computational overhead for embedded platforms or fail to achieve privacy protection and good model utility at the same time. Moreover, many defenses can be easily bypassed by adaptive adversaries who have obtained the defense details. To address these limitations, we propose SVDefense, a novel defense framework against GIAs that leverages the truncated Singular Value Decomposition (SVD) to obfuscate gradient updates. SVDefense introduces three key innovations, a Self-Adaptive Energy Threshold that adapts to client vulnerability, a Channel-Wise Weighted Approximation that selectively preserves essential gradient information for effective model training while enhancing privacy protection, and a Layer-Wise Weighted Aggregation for effective model aggregation under class imbalance. Our extensive evaluation shows that SVDefense outperforms existing defenses across multiple applications, including image classification, human activity recognition, and keyword spotting, by offering robust privacy protection with minimal impact on model accuracy. Furthermore, SVDefense is practical for deployment on various resource-constrained embedded platforms. We will make our code publicly available upon paper acceptance.

View More Papers

Identifying Logical Vulnerabilities in QUIC Implementations

Kaihua Wang (Tsinghua University), Jianjun Chen (Tsinghua University), Pinji Chen (Tsinghua University), Jianwei Zhuge (Tsinghua University), Jiaju Bai (Beihang University), Haixin Duan (Tsinghua University)

Read More

ropbot: Reimaging Code Reuse Attack Synthesis

Kyle Zeng (Arizona State University), Moritz Schloegel (CISPA Helmholtz Center for Information Security), Christopher Salls (UC Santa Barbara), Adam Doupé (Arizona State University), Ruoyu Wang (Arizona State University), Yan Shoshitaishvili (Arizona State University), Tiffany Bao (Arizona State University)

Read More

SocialStego: A Steganography Tool for the Modern Era of...

Branden Palacio (Marquette University), Keyang Yu (Marquette University)

Read More