all AI news
One-shot Empirical Privacy Estimation for Federated Learning
April 19, 2024, 4:42 a.m. | Galen Andrew, Peter Kairouz, Sewoong Oh, Alina Oprea, H. Brendan McMahan, Vinith M. Suriyakumar
cs.LG updates on arXiv.org arxiv.org
Abstract: Privacy estimation techniques for differentially private (DP) algorithms are useful for comparing against analytical bounds, or to empirically measure privacy loss in settings where known analytical bounds are not tight. However, existing privacy auditing techniques usually make strong assumptions on the adversary (e.g., knowledge of intermediate model iterates or the training data distribution), are tailored to specific tasks, model architectures, or DP algorithm, and/or require retraining the model many times (typically on the order of …
abstract algorithms arxiv assumptions cs.cr cs.lg federated learning however intermediate knowledge loss privacy type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Machine Learning Engineer
@ Samsara | Canada - Remote