all InfoSec news
Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
Feb. 29, 2024, 5:11 a.m. | Yilin Yang, Kamil Adamczewski, Danica J. Sutherland, Xiaoxiao Li, Mijung Park
cs.CR updates on arXiv.org arxiv.org
Abstract: Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features it allows us to summarize and privatize the data distribution once, which we can repeatedly use during generator training without further privacy loss. An important question in this framework is, then, what features are useful to distinguish between real and synthetic data distributions, and whether those enable us to generate quality synthetic data. This work …
arxiv can cs.cr cs.cv cs.lg data distribution features generator important loss metric mmd privacy private private data question training
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Senior PAM Security Engineer
@ Experian | Hyderabad, India
Cybersecurity Analyst II
@ Spry Methods | Washington, DC (Hybrid)
Cyber Security Engineer
@ Expleo | Gothenburg, AC, Sweden
Cybersecurity – Information System Security Manager (ISSM)
@ Boeing | USA - Albuquerque, NM
Senior Security Engineer - Canada
@ DataVisor | Ontario, Canada - Remote
Cybersecurity Architect
@ HARMAN International | JP Tokyo 3-5-7 Ariake Koto-ku