all InfoSec news
Increasing Confidence in Adversarial Robustness Evaluations. (arXiv:2206.13991v1 [cs.LG])
June 29, 2022, 1:20 a.m. | Roland S. Zimmermann, Wieland Brendel, Florian Tramer, Nicholas Carlini
cs.CR updates on arXiv.org arxiv.org
Hundreds of defenses have been proposed to make deep neural networks robust
against minimal (adversarial) input perturbations. However, only a handful of
these defenses held up their claims because correctly evaluating robustness is
extremely challenging: Weak attacks often fail to find adversarial examples
even if they unknowingly exist, thereby making a vulnerable network look
robust. In this paper, we propose a test to identify weak attacks, and thus
weak defense evaluations. Our test slightly modifies a neural network to
guarantee …
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
Program Associate, Cyber Risk
@ Kroll | Toronto, ONT, Canada
Cybersecurity Operations Engineer 2
@ Humana | Remote US
Vice President - Lead Security Engineer (SECS04)
@ JPMorgan Chase & Co. | Columbus, OH, United States
Security Specialist
@ BGIS | Markham, ON, Canada