all InfoSec News
Cross-silo Federated Learning with Record-level Personalized Differential Privacy
July 2, 2024, 4:14 a.m. | Junxu Liu, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng
cs.CR updates on arXiv.org arxiv.org
Abstract: Federated learning (FL) enhanced by differential privacy has emerged as a popular approach to better safeguard the privacy of client-side data by protecting clients' contributions during the training process. Existing solutions typically assume a uniform privacy budget for all records and provide one-size-fits-all solutions that may not be adequate to meet each record's privacy requirement. In this paper, we explore the uncharted territory of cross-silo FL with record-level personalized differential privacy. We devise a novel …
arxiv budget client clients client-side cs.ai cs.cr cs.lg data differential privacy federated federated learning may popular privacy process protecting record records safeguard size solutions training
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
All-Source Analyst (Watch Floor) - Senior
@ Global Dimensions | Columbia, Maryland, United States
Field Account Executive
@ Darktrace | Kentucky, United States
Technical Operations Engineer - International
@ Anduril | London, England, United Kingdom
Associate Analyst - Managed Security Services
@ Millennium IT ESP | Madhupur Upazila, Dhaka Division, Bangladesh
Associate Analyst - Managed Security Services
@ Millennium IT ESP | Klang, Selangor, Malaysia
Associate Analyst - Managed Security Services
@ Millennium IT ESP | Colombo, WP, Sri Lanka