all InfoSec news
Beyond Noise: Privacy-Preserving Decentralized Learning with Virtual Nodes
April 16, 2024, 4:11 a.m. | Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec, Laurent Massoulie, Rafael Pires, Rishi Sharma, Martijn de Vos
cs.CR updates on arXiv.org arxiv.org
Abstract: Decentralized learning (DL) enables collaborative learning without a server and without training data leaving the users' devices. However, the models shared in DL can still be used to infer training data. Conventional privacy defenses such as differential privacy and secure aggregation fall short in effectively safeguarding user privacy in DL. We introduce Shatter, a novel DL approach in which nodes create virtual nodes (VNs) to disseminate chunks of their full model on their behalf. This …
aggregation arxiv beyond can cs.ai cs.cr cs.dc cs.lg data decentralized defenses devices differential privacy effectively nodes noise privacy server training training data virtual
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
Senior Security Architect - Northwest region (Remote)
@ GuidePoint Security LLC | Remote
Senior Consultant, Cyber Security Architecture
@ 6point6 | Manchester, United Kingdom
Junior Security Architect
@ IQ-EQ | Port Louis, Mauritius
Senior Detection & Response Engineer
@ Expel | Remote
Cyber Security Systems Engineer ISSE Splunk
@ SAP | Southbank (Melbourne), VIC, AU, 3006