Speaker: Sebastian Angel
Location: Soda 510
Date: September 29, 2023
Time: 11am-12pm PST
Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning
Abstract: In this talk I will discuss Flamingo, a system for secure aggregation of data across a large set of clients. In secure aggregation, a server sums up the private inputs of clients and obtains the result without learning anything about the individual inputs beyond what is implied by the final sum. Flamingo works particularly well in the multi-round setting found in federated learning
in which many consecutive additions (averages) of model weights are performed to derive a good model. Furthermore, Flamingo can tolerate the failure of clients (e.g., clients that go offline) in the middle of the computation. Our implementation of Flamingo shows that it can securely train a neural network on the (Extended) MNIST and CIFAR-100 datasets significantly quicker than all prior secure aggregation systems, and the model converges without a loss in accuracy, compared to a non-private federated learning system.
Sebastian Angel is the Raj and Neera Singh Assistant Professor at the University of Pennsylvania. He is the recipient of an NSF Career Award, a JP Morgan Chase Faculty Award, and the ACM SIGOPS Doctoral Dissertation Award. Sebastian works on systems, security, and privacy. His recent work includes making expensive cryptography easier to use and more efficient, designing large scale systems for privately querying and aggregating data, and devising a more accountable and private framework to finance the free web.