all InfoSec news
On Convex Optimization with Semi-Sensitive Features
June 28, 2024, 4:20 a.m. | Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
cs.CR updates on arXiv.org arxiv.org
Abstract: We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the Label DP setting where only the label is sensitive. We give improved upper and lower bounds on the excess risk for DP-ERM. In particular, we show that the error only scales polylogarithmically in terms of the sensitive domain size, improving upon previous results that scale polynomially in the sensitive domain …
arxiv cs.cr cs.ds cs.lg excess features minimization optimization private problem risk semi sensitive study under
More from arxiv.org / cs.CR updates on arXiv.org
Kirchhoff Meets Johnson: In Pursuit of Unconditionally Secure Communication
2 days, 15 hours ago |
arxiv.org
Understanding Routing-Induced Censorship Changes Globally
2 days, 15 hours ago |
arxiv.org
Investigating and Defending Shortcut Learning in Personalized Diffusion Models
2 days, 15 hours ago |
arxiv.org
Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing
2 days, 15 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
Technical Product Engineer
@ Palo Alto Networks | Tel Aviv-Yafo, Israel
Azure Cloud Architect
@ Version 1 | Dublin, Ireland
Junior Pen Tester
@ Vertiv | Pune, India
Information Security GRC Director
@ IQ-EQ | Hyderabad, India
Senior Technical Analyst
@ Fidelity International | Gurgaon Office
Security Engineer II
@ Microsoft | Redmond, Washington, United States