Communication-Efficient and Byzantine-Robust Differentially Private Federated Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Communications Letters"
DOI: 10.1109/lcomm.2022.3180113
Abstract: Federated learning, as a novel paradigm of machine learning, is facing a series of challenges such as efficiency, privacy and robustness. The recently proposed EF-DP- SIGNSGD provides theoretical privacy protection for SIGNSGD with majority vote… read more here.
Keywords: efficient byzantine; communication efficient; federated learning; byzantine ... See more keywords
Privacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2022.3196274
Abstract: Federated learning enables clients to train a machine learning model jointly without sharing their local data. However, due to the centrality of federated learning framework and the untrustworthiness of clients, traditional federated learning solutions are… read more here.
Keywords: blockchain; preserving byzantine; federated learning; privacy preserving ... See more keywords