Random Client Selection on Contrastive Federated Learning for Tabular Data

2025-05-16

AI Summary

To address privacy leakage from gradient inversion attacks in contrastive federated learning (CFL), this paper proposes a lightweight defense mechanism based on random client selection, specifically designed for collaborative tabular data modeling in vertical federated learning. Unlike fixed-topology CFL, our approach systematically demonstrates—both theoretically and empirically—that random client sampling significantly enhances robustness against gradient leakage. Experiments across multiple benchmark tabular datasets show that the method reduces attack success rates by over 60%, without compromising model convergence or predictive accuracy. The key contribution lies in revealing and validating client randomization as an effective implicit regularizer for privacy protection in CFL, establishing a novel paradigm for secure federated learning that requires no additional noise injection or communication overhead.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Vertical Federated Learning (VFL) has revolutionised collaborative machine learning by enabling privacy-preserving model training across multiple parties. However, it remains vulnerable to information leakage during intermediate computation sharing. While Contrastive Federated Learning (CFL) was introduced to mitigate these privacy concerns through representation learning, it still faces challenges from gradient-based attacks. This paper presents a comprehensive experimental analysis of gradient-based attacks in CFL environments and evaluates random client selection as a defensive strategy. Through extensive experimentation, we demonstrate that random client selection proves particularly effective in defending against gradient attacks in the CFL network. Our findings provide valuable insights for implementing robust security measures in contrastive federated learning systems, contributing to the development of more secure collaborative learning frameworks

Problem

• Analyzing gradient-based attacks in Contrastive Federated Learning (CFL)
• Evaluating random client selection as defense against gradient attacks
• Enhancing privacy and security in collaborative tabular data learning

Innovation

• Random client selection defends gradient attacks
• Contrastive Federated Learning enhances privacy
• Experimental analysis validates security measures