Sparsification Under Siege: Defending Against Poisoning Attacks in Communication-Efficient Federated Learning

2025-04-30

AI Summary

In sparse federated learning (FL), poisoning attacks exploit update sparsity to evade detection, rendering existing defenses ineffective. To address this, we propose FLARE—a robust, communication-efficient defense framework that imposes no additional communication overhead. FLARE’s core innovation lies in the first joint exploitation of (i) sparse index mask consistency checking and (ii) sign-level similarity analysis of model updates, enabling a lightweight, yet effective, anomaly detection mechanism. This is synergistically combined with a consensus-based client filtering strategy. Extensive evaluation across multiple benchmark datasets and under diverse strong adversarial poisoning attacks demonstrates that FLARE improves defense success rate by over 40% compared to state-of-the-art methods, while strictly preserving the same communication efficiency as baseline sparse FL. FLARE thus bridges a critical gap in the security of sparse federated learning.

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

Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, yet it faces significant challenges in communication efficiency and vulnerability to poisoning attacks. While sparsification techniques mitigate communication overhead by transmitting only critical model parameters, they inadvertently amplify security risks: adversarial clients can exploit sparse updates to evade detection and degrade model performance. Existing defense mechanisms, designed for standard FL communication scenarios, are ineffective in addressing these vulnerabilities within sparsified FL. To bridge this gap, we propose FLARE, a novel federated learning framework that integrates sparse index mask inspection and model update sign similarity analysis to detect and mitigate poisoning attacks in sparsified FL. Extensive experiments across multiple datasets and adversarial scenarios demonstrate that FLARE significantly outperforms existing defense strategies, effectively securing sparsified FL against poisoning attacks while maintaining communication efficiency.

Problem

• Defending against poisoning attacks in federated learning
• Addressing security risks in sparsified FL updates
• Ensuring communication efficiency while mitigating adversarial exploits

Innovation

• Integrates sparse index mask inspection
• Uses model update sign similarity analysis
• Detects and mitigates poisoning attacks effectively