Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix

Maximilian Lam, Gu-Yeon Wei, David Brooks 0001, Vijay Janapa Reddi, Michael Mitzenmacher. Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix. In Marina Meila, Tong Zhang 0001, editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Volume 139 of Proceedings of Machine Learning Research, pages 5959-5968, PMLR, 2021. [doi]

Abstract

Abstract is missing.