all InfoSec news
Cross-Input Certified Training for Universal Perturbations
May 16, 2024, 4:12 a.m. | Changming Xu, Gagandeep Singh
cs.CR updates on arXiv.org arxiv.org
Abstract: Existing work in trustworthy machine learning primarily focuses on single-input adversarial perturbations. In many real-world attack scenarios, input-agnostic adversarial attacks, e.g. universal adversarial perturbations (UAPs), are much more feasible. Current certified training methods train models robust to single-input perturbations but achieve suboptimal clean and UAP accuracy, thereby limiting their applicability in practical applications. We propose a novel method, CITRUS, for certified training of networks robust against UAP attackers. We show in an extensive evaluation across …
accuracy adversarial adversarial attacks arxiv attack attacks certified cs.cr cs.lg current input machine machine learning real single train training uap work world
More from arxiv.org / cs.CR updates on arXiv.org
Proactive Detection of Voice Cloning with Localized Watermarking
2 days, 21 hours ago |
arxiv.org
NFT Wash Trading: Direct vs. Indirect Estimation
2 days, 21 hours ago |
arxiv.org
Backdoor Attack with Sparse and Invisible Trigger
2 days, 21 hours ago |
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
Senior Security Researcher - Linux MacOS EDR (Cortex)
@ Palo Alto Networks | Tel Aviv-Yafo, Israel
Sr. Manager, NetSec GTM Programs
@ Palo Alto Networks | Santa Clara, CA, United States
SOC Analyst I
@ Fortress Security Risk Management | Cleveland, OH, United States