Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning
arXiv:2106.03328
Abstract
Secure aggregation is a critical component in federated learning (FL), which enables the server to learn the aggregate model of the users without observing their local models. Conventionally, secure aggregation algorithms focus only on ensuring the privacy of individual users in a single training round. We contend that such designs can lead to significant privacy leakages over multiple training rounds, due to partial user selection/participation at each round of FL. In fact, we show that the conventional random user selection strategies in FL lead to leaking users' individual models within number of rounds that is linear in the number of users. To address this challenge, we introduce a secure aggregation framework, Multi-RoundSecAgg, with multi-round privacy guarantees. In particular, we introduce a new metric to quantify the privacy guarantees of FL over multiple training rounds, and develop a structured user selection strategy that guarantees the long-term privacy of each user (over any number of training rounds). Our framework also carefully accounts for the fairness and the average number of participating users at each round. Our experiments on MNIST and CIFAR-10 datasets in the IID and the non-IID settings demonstrate the performance improvement over the baselines, both in terms of privacy protection and test accuracy.
References in corpus (6)
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
- Optimal Client Sampling for Federated Learning
- Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
- Communication-Computation Efficient Secure Aggregation for Federated Learning
- The smallest singular value of random combinatorial matrices