all InfoSec news
Closed-Form Bounds for DP-SGD against Record-level Inference
Feb. 23, 2024, 5:11 a.m. | Giovanni Cherubin, Boris K\"opf, Andrew Paverd, Shruti Tople, Lukas Wutschitz, Santiago Zanella-B\'eguelin
cs.CR updates on arXiv.org arxiv.org
Abstract: Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an $(\varepsilon,\delta)$-DP guarantee, meaningful bounds require a small enough privacy budget (i.e., injecting a large amount of noise), which results in a large loss in utility. This paper presents a new approach to evaluate the privacy of machine learning models against specific …
algorithms arxiv attacks budget cs.cr cs.lg delta guarantee large machine machine learning machine learning models meaningful privacy private record resilience
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
Cyber Security Culture – Communication and Content Specialist
@ H&M Group | Stockholm, Sweden
Container Hardening, Sr. (Remote | Top Secret)
@ Rackner | San Antonio, TX
GRC and Information Security Analyst
@ Intertek | United States
Information Security Officer
@ Sopra Steria | Bristol, United Kingdom
Casual Area Security Officer South Down Area
@ TSS | County Down, United Kingdom