all InfoSec news
On the Importance of Architecture and Feature Selection in Differentially Private Machine Learning. (arXiv:2205.06720v1 [cs.CR])
May 16, 2022, 1:20 a.m. | Wenxuan Bao, Luke A. Bauer, Vincent Bindschaedler
cs.CR updates on arXiv.org arxiv.org
We study a pitfall in the typical workflow for differentially private machine
learning. The use of differentially private learning algorithms in a "drop-in"
fashion -- without accounting for the impact of differential privacy (DP) noise
when choosing what feature engineering operations to use, what features to
select, or what neural network architecture to use -- yields overly complex and
poorly performing models. In other words, by anticipating the impact of DP
noise, a simpler and more accurate alternative model could …
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
Information Security Engineers
@ D. E. Shaw Research | New York City
Security Solution Architect
@ Civica | London, England, United Kingdom
Information Security Officer (80-100%)
@ SIX Group | Zurich, CH
Cloud Information Systems Security Engineer
@ Analytic Solutions Group | Chantilly, Virginia, United States
SRE Engineer & Security Software Administrator
@ Talan | Mexico City, Spain