all InfoSec news
FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models
March 6, 2024, 5:11 a.m. | Younghan Lee, Yungi Cho, Woorim Han, Ho Bae, Yunheung Paek
cs.CR updates on arXiv.org arxiv.org
Abstract: Federated Learning (FL) thrives in training a global model with numerous clients by only sharing the parameters of their local models trained with their private training datasets. Therefore, without revealing the private dataset, the clients can obtain a deep learning (DL) model with high performance. However, recent research proposed poisoning attacks that cause a catastrophic loss in the accuracy of the global model when adversaries, posed as benign clients, are present in a group of …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Security Analysis Senior Analyst
@ NTT DATA | Bengaluru, KA, IN
SAP NS2 SIEM Engineering Manager - Herndon (Hybrid)
@ SAP | Herndon, VA, US, 20171
Security Architect - Infrastructure
@ Yorkshire Water | Bradford, GB
Information System Security Officer, Journeyman (Secret)
@ Resource Management Concepts, Inc. | Patuxent River, Maryland, United States
Technology Information Security GRC Senior
@ KPMG India | Gurgaon, Haryana, India
Principal CyberSecurity Engineer
@ DTCC | Dallas, TX, United States