all InfoSec news
How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection. (arXiv:2206.14157v1 [cs.LG])
June 29, 2022, 1:20 a.m. | Mantas Mazeika, Bo Li, David Forsyth
cs.CR updates on arXiv.org arxiv.org
Model stealing attacks present a dilemma for public machine learning APIs. To
protect financial investments, companies may be forced to withhold important
information about their models that could facilitate theft, including
uncertainty estimates and prediction explanations. This compromise is harmful
not only to users but also to external transparency. Model stealing defenses
seek to resolve this dilemma by making models harder to steal while preserving
utility for benign users. However, existing defenses have poor performance in
practice, either requiring enormous …
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
Intermediate Security Engineer, (Incident Response, Trust & Safety)
@ GitLab | Remote, US
Journeyman Cybersecurity Triage Analyst
@ Peraton | Linthicum, MD, United States
Project Manager II - Compliance
@ Critical Path Institute | Tucson, AZ, USA
Junior System Engineer (m/w/d) Cyber Security 1
@ Deutsche Telekom | Leipzig, Deutschland