Sparsification Under Siege: Defending Against Poisoning Attacks in Communication-Efficient Federated Learning
This addresses security vulnerabilities for federated learning systems using sparsification, representing an incremental improvement over existing defenses.
The paper tackles the problem of poisoning attacks in communication-efficient federated learning using sparsification, and the result is that their proposed FLARE framework significantly outperforms existing defenses in securing sparsified FL while maintaining efficiency.
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.