all InfoSec news
Improved and Interpretable Defense to Transferred Adversarial Examples by Jacobian Norm with Selective Input Gradient Regularization. (arXiv:2207.13036v2 [cs.LG] UPDATED)
July 28, 2022, 1:20 a.m. | Deyin Liu, Lin Wu, Farid Boussaid, Mohammed Bennamoun
cs.CR updates on arXiv.org arxiv.org
Deep neural networks (DNNs) are known to be vulnerable to adversarial
examples that are crafted with imperceptible perturbations, i.e., a small
change in an input image can induce a mis-classification, and thus threatens
the reliability of deep learning based deployment systems. Adversarial training
(AT) is often adopted to improve the robustness of DNNs through training a
mixture of corrupted and clean data. However, most of AT based methods are
ineffective in dealing with \textit{transferred adversarial examples} which are
generated to …
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
Digital Trust Cyber Transformation Senior
@ KPMG India | Mumbai, Maharashtra, India
Security Consultant, Assessment Services - SOC 2 | Remote US
@ Coalfire | United States
Sr. Systems Security Engineer
@ Effectual | Washington, DC
Cyber Network Engineer
@ SonicWall | Woodbridge, Virginia, United States
Security Architect
@ Nokia | Belgium