all InfoSec news
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
Feb. 27, 2024, 5:11 a.m. | Andrew C. Cullen, Shijie Liu, Paul Montague, Sarah M. Erfani, Benjamin I. P. Rubinstein
cs.CR updates on arXiv.org arxiv.org
Abstract: In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the very models they help to protect? Our new \emph{Certification Aware Attack} exploits certifications to produce computationally efficient norm-minimising adversarial examples $74 \%$ more often than comparable attacks, while reducing the median perturbation norm by more than $10\%$. While these attacks can be …
adversarial arxiv ask attack aware can certificates certification certifications compromise cs.cr cs.lg examples exploits important instance play protect robustness role
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
Corporate Intern - Information Security (Year Round)
@ Associated Bank | US WI Remote
Senior Offensive Security Engineer
@ CoStar Group | US-DC Washington, DC