all InfoSec news
FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning
Feb. 28, 2024, 5:11 a.m. | Tianhang Zheng, Baochun Li
cs.CR updates on arXiv.org arxiv.org
Abstract: Federated learning has recently emerged as a decentralized approach to learn a high-performance model without access to user data. Despite its effectiveness, federated learning gives malicious users opportunities to manipulate the model by uploading poisoned model updates to the server. In this paper, we propose a review mechanism called FedReview to identify and decline the potential poisoned updates in federated learning. Under our mechanism, the server randomly assigns a subset of clients as reviewers to …
access arxiv cs.ai cs.cr cs.lg data decentralized decentralized approach federated federated learning high learn malicious mechanism opportunities performance review server updates user data
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Consultant Sécurité SI H/F Gouvernance - Risques - Conformité - Nantes
@ Hifield | Saint-Herblain, France
L2 Security - Senior Security Engineer
@ Paytm | Noida, Uttar Pradesh
GRC Integrity Program Manager
@ Meta | Bellevue, WA | Menlo Park, CA | Washington, DC | New York City
Consultant Active Directory H/F
@ Hifield | Sèvres, France
Consultant PCI-DSS H/F
@ Hifield | Sèvres, France
Head of Security Operations
@ Canonical Ltd. | Home based - Americas, EMEA