all InfoSec News
OASIS: Offsetting Active Reconstruction Attacks in Federated Learning
June 5, 2024, 4:12 a.m. | Tre' R. Jeter, Truc Nguyen, Raed Alharbi, My T. Thai
cs.CR updates on arXiv.org arxiv.org
Abstract: Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. For that reason, FL has found its use in various domains, from healthcare to industrial engineering, especially where data cannot be easily exchanged due to sensitive information or privacy laws. However, recent research has demonstrated that FL protocols can be easily compromised by active reconstruction attacks executed by dishonest servers. These attacks involve the malicious modification …
arxiv attacks attention cs.ai cs.cr data domains efficiency engineering federated federated learning found healthcare industrial information model training oasis privacy protect sensitive sensitive information training user privacy
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Head of IT Governance IT Risk IT Outsourcing
@ State Street | Munich, Germany
Information Assurance Engineer (Engineer Info Assurance 3) 19608
@ HII | Annapolis Junction, MD, Maryland, United States
VP control design and Development
@ State Street | Dublin 2, Ireland
Channel & Alliances Solution Architect
@ Trend Micro | US Off-Site
Senior DevOps Engineer (f/m/d)
@ E.ON | Essen, DE
DevOps Engineer with OpenShift & Kubernetes
@ Peraton | Arlington, VA, United States