FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning

Abstract

Recent attacks on federated learning demonstrate that keeping the training data on clients' devices does not provide sufficient privacy, as the model parameters shared by clients can leak information about their training data. A 'secure aggregation' protocol enables the server to aggregate clients' models in a privacy-preserving manner. However, existing secure aggregation protocols incur high computation/communication costs, especially when the number of model parameters is larger than the number of clients participating in an iteration -- a typical scenario in federated learning. In this paper, we propose a secure aggregation protocol, FastSecAgg, that is efficient in terms of computation and communication, and robust to client dropouts. The main building block of FastSecAgg is a novel multi-secret sharing scheme, FastShare, based on the Fast Fourier Transform (FFT), which may be of independent interest. FastShare is information-theoretically secure, and achieves a trade-off between the number of secrets, privacy threshold, and dropout tolerance. Riding on the capabilities of FastShare, we prove that FastSecAgg is (i) secure against the server colluding with 'any' subset of some constant fraction (e.g. $\sim 10\%$) of the clients in the honest-but-curious setting; and (ii) tolerates dropouts of a 'random' subset of some constant fraction (e.g. $\sim 10\%$) of the clients. FastSecAgg achieves significantly smaller computation cost than existing schemes while achieving the same (orderwise) communication cost. In addition, it guarantees security against adaptive adversaries, which can perform client corruptions dynamically during the execution of the protocol.

Shorter version accepted in ICML Workshop on Federated Learning, July 2020, and CCS Workshop on Privacy-Preserving Machine Learning in Practice, November 2020

References in corpus (8)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Robust Aggregation for Federated Learning
• The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
• Mitigating Sybils in Federated Learning Poisoning
• Universal Secure Network Coding via Rank-Metric Codes
• Secure Byzantine-Robust Machine Learning
• Byzantine-Resilient Secure Federated Learning

Cited by in corpus (16)

• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• Efficient Dropout-resilient Aggregation for Privacy-preserving Machine Learning
• Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning
• Privacy-Preserving Machine Learning: Methods, Challenges and Directions
• The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Training Fair Models in Federated Learning without Data Privacy Infringement
• Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning
• Secure Weighted Aggregation for Federated Learning
• Secure Aggregation with Heterogeneous Quantization in Federated Learning
• Secure Aggregation for Buffered Asynchronous Federated Learning
• ScionFL: Efficient and Robust Secure Quantized Aggregation
• The Capacity of 3 User Linear Computation Broadcast
• On the Generic Capacity of $K$-User Symmetric Linear Computation Broadcast
• Federated learning with differential privacy and an untrusted aggregator
• Practical and Light-weight Secure Aggregation for Federated Submodel Learning