all InfoSec news
Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent. (arXiv:2102.05855v5 [stat.ML] UPDATED)
Sept. 12, 2022, 1:20 a.m. | Rishav Chourasia, Jiayuan Ye, Reza Shokri
cs.CR updates on arXiv.org arxiv.org
What is the information leakage of an iterative randomized learning algorithm
about its training data, when the internal state of the algorithm is
\emph{private}? How much is the contribution of each specific training epoch to
the information leakage through the released model? We study this problem for
noisy gradient descent algorithms, and model the \emph{dynamics} of R\'enyi
differential privacy loss throughout the training process. Our analysis traces
a provably \emph{tight} bound on the R\'enyi divergence between the pair of
probability …
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
Digital Trust Cyber Transformation Senior
@ KPMG India | Mumbai, Maharashtra, India
Security Consultant, Assessment Services - SOC 2 | Remote US
@ Coalfire | United States
Sr. Systems Security Engineer
@ Effectual | Washington, DC
Cyber Network Engineer
@ SonicWall | Woodbridge, Virginia, United States
Security Architect
@ Nokia | Belgium