Web: http://arxiv.org/abs/2208.00539

Aug. 5, 2022, 1:20 a.m. | Ali Borji

cs.CR updates on arXiv.org arxiv.org

Short answer: Yes, Long answer: No! Indeed, research on adversarial
robustness has led to invaluable insights helping us understand and explore
different aspects of the problem. Many attacks and defenses have been proposed
over the last couple of years. The problem, however, remains largely unsolved
and poorly understood. Here, I argue that the current formulation of the
problem serves short term goals, and needs to be revised for us to achieve
bigger gains. Specifically, the bound on perturbation has created …

adversarial current problem research robustness

More from arxiv.org / cs.CR updates on arXiv.org

Sr. Security Consultant for Aerospace & Satellite Professional Services , Aerospace & Satellite Professional Services

@ Amazon.com | US, FL, Virtual Location - Florida

Cyber Threat Intelligence (CTI) Analyst

@ XOR Security | Alexandria, VA

SC2022-002063 Cyber Security Incident Investigator (NS) - TUE 30 Aug Relaunch

@ EMW, Inc. | Mons, Wallonia, Belgium

Senior SOC Analyst

@ XOR Security | Alexandria, VA

Cyber Protect Expert Engineer

@ Acronis | Bucharest, Bucharest, Romania

Senior Consultant, PCI QSA | Remote US

@ Coalfire | Denver, CO