Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
This addresses security and privacy issues in federated learning for decentralized applications, though it appears incremental as it builds on existing methods to combine defenses.
The paper tackles the problem of security threats like gradient inversion and model poisoning in federated learning by introducing Tazza, a framework that uses weight shuffling and shuffled model validation to enhance resilience and maintain data confidentiality, achieving up to 6.7x improved computational efficiency without performance loss.
Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gradient inversion and model poisoning by malicious clients, remain unresolved. Existing solutions often address these issues separately, sacrificing either system robustness or model accuracy. This work introduces Tazza, a secure and efficient federated learning framework that simultaneously addresses both challenges. By leveraging the permutation equivariance and invariance properties of neural networks via weight shuffling and shuffled model validation, Tazza enhances resilience against diverse poisoning attacks, while ensuring data confidentiality and high model accuracy. Comprehensive evaluations on various datasets and embedded platforms show that Tazza achieves robust defense with up to 6.7x improved computational efficiency compared to alternative schemes, without compromising performance.