Random Client Selection on Contrastive Federated Learning for Tabular Data

2025/05/16 by Achmad Ginanjar, Xue Li, Ginanjar, Achmad +5
Computer Science · #Advanced Graph Neural Networks #Cryptography and Data Security #Cryptography and Security (cs.CR) #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.2505.10759

openalex publication_date 2025/05/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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

Citations

• FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information
• Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data
• Byzantine-Resilient Secure Federated Learning
• Data Poisoning Attacks Against Federated Learning Systems
• A Simple Framework for Contrastive Learning of Visual Representations
• Introducing LETOR 4.0 Datasets

Related

• Defending against Reconstruction Attack in Vertical Federated Learning
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
• Membership Information Leakage in Federated Contrastive Learning
• LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning
• Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks