Decentralized and Secure Aggregation in Federated Learning

Abstract

Federated learning (FL) is a machine learning technique where multiple clients with local data collaborate in training a machine learning model. However, this centralization of sensitive model updates incurs security and privacy issues. A malicious aggregator can launch inference attacks to violate the privacy of clients' private data from local models and explore sensitive knowledge from global model. Trusted Execution Environment (TEE) based schemes offer secure enclaves to protect models privacy during the aggregation procedure. However, TEE technologies incur new functional and security assumptions, where a single vulnerability could undermine the trusted system. Cryptographic schemes such as homomorphic encryption (HE), differential privacy (DP) and secret sharing (SS) cannot achieve the simultaneous requirements of efficiency, accuracy and privacy currently. In this paper, we present DoshFL that avoids expensive cryptographic operations and enables tunable trade-off between privacy and efficiency in federated learning for model asset protection.