Score: 2

Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks

Published: March 13, 2025 | arXiv ID: 2503.11514v1

By: Pengxin Guo , Runxi Wang , Shuang Zeng and more

BigTech Affiliations: Stanford University

Potential Business Impact:

Protects private info from sneaky computer learning.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

Federated Learning (FL) has emerged as a promising privacy-preserving collaborative model training paradigm without sharing raw data. However, recent studies have revealed that private information can still be leaked through shared gradient information and attacked by Gradient Inversion Attacks (GIA). While many GIA methods have been proposed, a detailed analysis, evaluation, and summary of these methods are still lacking. Although various survey papers summarize existing privacy attacks in FL, few studies have conducted extensive experiments to unveil the effectiveness of GIA and their associated limiting factors in this context. To fill this gap, we first undertake a systematic review of GIA and categorize existing methods into three types, i.e., \textit{optimization-based} GIA (OP-GIA), \textit{generation-based} GIA (GEN-GIA), and \textit{analytics-based} GIA (ANA-GIA). Then, we comprehensively analyze and evaluate the three types of GIA in FL, providing insights into the factors that influence their performance, practicality, and potential threats. Our findings indicate that OP-GIA is the most practical attack setting despite its unsatisfactory performance, while GEN-GIA has many dependencies and ANA-GIA is easily detectable, making them both impractical. Finally, we offer a three-stage defense pipeline to users when designing FL frameworks and protocols for better privacy protection and share some future research directions from the perspectives of attackers and defenders that we believe should be pursued. We hope that our study can help researchers design more robust FL frameworks to defend against these attacks.

Country of Origin
πŸ‡­πŸ‡° πŸ‡ΊπŸ‡Έ Hong Kong, United States

Page Count
21 pages

Category
Computer Science:
Cryptography and Security