June 27, 2022, 1:20 a.m. | Chengyin Hu, Weiwen Shi

cs.CR updates on arXiv.org arxiv.org

Although deep neural networks (DNNs) are known to be fragile, no one has
studied the effects of zooming-in and zooming-out of images in the physical
world on DNNs performance. In this paper, we demonstrate a novel physical
adversarial attack technique called Adversarial Zoom Lens (AdvZL), which uses a
zoom lens to zoom in and out of pictures of the physical world, fooling DNNs
without changing the characteristics of the target object. The proposed method
is so far the only adversarial …

adversarial attack physical world zoom

SOC 2 Manager, Audit and Certification

@ Deloitte | US and CA Multiple Locations

Information Security Engineers

@ D. E. Shaw Research | New York City

Security Officer Level 1 (L1)

@ NTT DATA | Virginia, United States of America

Alternance - Analyste VOC - Cybersécurité - Île-De-France

@ Sopra Steria | Courbevoie, France

Senior Security Researcher, SIEM

@ Huntress | Remote US or Remote CAN

Cyber Security Engineer Lead

@ ASSYSTEM | Bridgwater, United Kingdom