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
IDEA: Invariant Defense for Graph Adversarial Robustness
1 day, 10 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
1 day, 10 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
1 day, 10 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Open-Source Intelligence (OSINT) Policy Analyst (TS/SCI)
@ WWC Global | Reston, Virginia, United States
Security Architect (DevSecOps)
@ EUROPEAN DYNAMICS | Brussels, Brussels, Belgium
Infrastructure Security Architect
@ Ørsted | Kuala Lumpur, MY
Contract Penetration Tester
@ Evolve Security | United States - Remote
Senior Penetration Tester
@ DigitalOcean | Canada