all InfoSec news
Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning?. (arXiv:2110.05057v4 [cs.LG] UPDATED)
Sept. 15, 2022, 1:20 a.m. | Guy Heller, Ethan Fetaya
cs.CR updates on arXiv.org arxiv.org
Bayesian learning via Stochastic Gradient Langevin Dynamics (SGLD) has been
suggested for differentially private learning. While previous research provides
differential privacy bounds for SGLD at the initial steps of the algorithm or
when close to convergence, the question of what differential privacy guarantees
can be made in between remains unanswered. This interim region is of great
importance, especially for Bayesian neural networks, as it is hard to guarantee
convergence to the posterior. This paper shows that using SGLD might result …
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
Check Team Members / Cyber Consultants / Pen Testers
@ Resillion | Birmingham, United Kingdom
Security Officer Field Training Officer- Full Time (Harrah's LV)
@ Caesars Entertainment | Las Vegas, NV, United States
Cybersecurity Subject Matter Expert (SME)
@ SMS Data Products Group, Inc. | Fort Belvoir, VA, United States
AWS Security Engineer
@ IntelliPro Group Inc. | Palo Alto, CA
Information Security Analyst
@ Freudenberg Group | Alajuela