all InfoSec news
Expressive Losses for Verified Robustness via Convex Combinations
March 15, 2024, 4:10 a.m. | Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth, Alessio Lomuscio
cs.CR updates on arXiv.org arxiv.org
Abstract: In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance. As shown in recent work, better trade-offs between accuracy and robustness can be obtained by carefully coupling adversarial training with over-approximations. We hypothesize that the expressivity of a loss function, which we formalize as the ability to span a range of trade-offs between …
accuracy adversarial arxiv can case cs.cr cs.lg loss losses networks order performance robustness standard stat.ml trade trade-offs train verified work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Security Compliance Strategist
@ Grab | Petaling Jaya, Malaysia
Cloud Security Architect, Lead
@ Booz Allen Hamilton | USA, VA, McLean (1500 Tysons McLean Dr)