all InfoSec news
An automatic differentiation system for the age of differential privacy. (arXiv:2109.10573v2 [cs.LG] UPDATED)
April 6, 2022, 1:20 a.m. | Dmitrii Usynin, Alexander Ziller, Moritz Knolle, Andrew Trask, Kritika Prakash, Daniel Rueckert, Georgios Kaissis
cs.CR updates on arXiv.org arxiv.org
We introduce Tritium, an automatic differentiation-based sensitivity analysis
framework for differentially private (DP) machine learning (ML). Optimal noise
calibration in this setting requires efficient Jacobian matrix computations and
tight bounds on the L2-sensitivity. Our framework achieves these objectives by
relying on a functional analysis-based method for sensitivity tracking, which
we briefly outline. This approach interoperates naturally and seamlessly with
static graph-based automatic differentiation, which enables order-of-magnitude
improvements in compilation times compared to previous work. Moreover, we
demonstrate that optimising the …
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
Team Lead, Security Operations Center, Cyber Risk
@ Kroll | United Kingdom
Cyber Security Risk Analyst
@ College Board | Remote - Virginia
Lead - IT Security Engineer
@ Bosch Group | BENGALURU, India
Project Cybersecurity Manager
@ Alstom | Bengaluru, KA, IN
Security Consultant
@ CloudSEK | Bengaluru, Karnataka, India