FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning

FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning

Channel:
United States Google TechTalks
Subscribers:
348,000
Published on ● Video Link: https://www.youtube.com/watch?v=NwpcUVFSPng


Duration: 15:34
1,730 views
24

A Google TechTalk, 2020/7/30, presented by Swanand Kadhe, UC Berkeley
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. Therefore, it is crucial to develop ‘secure aggregation’ protocols that allow the server to aggregate client models in a privacy-preserving manner. In this work, 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.



Other Videos By Google TechTalks


2021-06-04Breaking the Communication-Privacy-Accuracy Trilemma
2021-06-04Cronus: Robust Knowledge Transfer for Federated Learning
2021-06-04Private Algorithms with Minimal Space
2021-06-04Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
2021-06-04Flower: A Friendly Federated Learning Framework
2021-06-04Lions, Skunks, and Kangaroos: Geo-Distributed Learning on the Flickr-Mammal Dataset
2021-06-04Secure Federated Learning in Adversarial Environments
2021-06-04Analyzing Model Poisoning Attacks on Federated Learning at Scale
2021-06-04Federated Design of Compact and Private DNNs
2021-06-04FL Meets Wireless: More than the sum of its parts
2021-06-04FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
2021-06-04On Heterogeneity in Federated Settings: Workshop on Federated Learning and Analytics Day 2 Keynote
2021-06-04Towards Responsible AI
2021-06-04Workshop on Federated Learning & Analytics: Pre-recorded Talks Day 1 Track 2 Q&A Privacy/Security
2021-06-04Context-Aware Local Differential Privacy
2021-06-04Semantic Adversarial Attacks for Privacy Protection
2021-06-04How Could the Mind be Storing Information?
2021-05-17Towards Reliable Machine Learning via Distributional Robustness
2021-05-10Advent of Code: Behind the Scenes
2021-04-212021 Blockly Developer Summit: Test Helpers
2021-04-212021 Blockly Developer Summit: Metrics Deep Dive