reserve 发表于 2025-3-30 10:56:24
978-3-031-51481-4The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerl没有贫穷 发表于 2025-3-30 14:21:03
http://reply.papertrans.cn/24/2339/233872/233872_52.pngPeristalsis 发表于 2025-3-30 19:41:02
http://reply.papertrans.cn/24/2339/233872/233872_53.pngEWER 发表于 2025-3-30 23:16:25
http://reply.papertrans.cn/24/2339/233872/233872_54.pngOffset 发表于 2025-3-31 03:16:21
https://doi.org/10.1007/978-3-642-11273-7y distributed (non-IID). In this work, we propose FLGuard, a novel byzantine-robust FL method that detects malicious clients and discards malicious local updates by utilizing the contrastive learning technique, which showed a tremendous improvement as a self-supervised learning method. With contrast