Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning

TL;DR

Tazza is a federated learning framework that enhances security against poisoning attacks and preserves data privacy by shuffling neural network parameters, achieving high accuracy and efficiency.

Contribution

It introduces a novel weight shuffling method leveraging neural network properties to improve robustness and privacy in federated learning.

Findings

Up to 6.7x improved computational efficiency

Robust defense against poisoning attacks

Maintains high model accuracy

Abstract

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.