all InfoSec news
Privacy Attacks in Decentralized Learning
Feb. 16, 2024, 5:10 a.m. | Abdellah El Mrini, Edwige Cyffers, Aur\'elien Bellet
cs.CR updates on arXiv.org arxiv.org
Abstract: Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph. The absence of direct communication between non-neighbor nodes might lead to the belief that users cannot infer precise information about the data of others. In this work, we demonstrate the opposite, by proposing the first attack against D-GD that enables a user (or set of …
a network arxiv attacks communication cs.cr cs.lg data decentralized graph information local network nodes non privacy sharing updates
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Emergency Management Invoice Compliance Reviewer
@ AC Disaster Consulting | Denver, Colorado, United States - Remote
Threat Intelligence Librarian
@ Microsoft | Cheltenham, Gloucestershire, United Kingdom
Cyber Content Operations Manager - Remote in UK
@ Immersive Labs | United Kingdom
(Junior) Security Engineer (m/w/d)
@ CHECK24 | Berlin, Germany
Cyber Security
@ Necurity Solutions | Bengaluru, Karnataka, India