all InfoSec news
Demystifying the Adversarial Robustness of Random Transformation Defenses. (arXiv:2207.03574v2 [cs.CR] UPDATED)
July 18, 2022, 1:20 a.m. | Chawin Sitawarin, Zachary Golan-Strieb, David Wagner
cs.CR updates on arXiv.org arxiv.org
Neural networks' lack of robustness against attacks raises concerns in
security-sensitive settings such as autonomous vehicles. While many
countermeasures may look promising, only a few withstand rigorous evaluation.
Defenses using random transformations (RT) have shown impressive results,
particularly BaRT (Raff et al., 2019) on ImageNet. However, this type of
defense has not been rigorously evaluated, leaving its robustness properties
poorly understood. Their stochastic properties make evaluation more challenging
and render many proposed attacks on deterministic models inapplicable. First,
we show …
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
Director, Data Security Lead
@ Mastercard | London, England (Angel Lane)
Security Officer L1
@ NTT DATA | Texas, United States of America
Sr. Staff Application Security Engineer
@ Aurora Innovation | Seattle, WA
Senior Penetration Testing Engineer
@ WPP | Chennai
Cyber Security - Senior Software Developer in Test
@ BlackBerry | Bengaluru, Residency Road