all InfoSec news
Attacking Transformers with Feature Diversity Adversarial Perturbation
March 14, 2024, 4:10 a.m. | Chenxing Gao, Hang Zhou, Junqing Yu, YuTeng Ye, Jiale Cai, Junle Wang, Wei Yang
cs.CR updates on arXiv.org arxiv.org
Abstract: Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications. Existing ViT adversarial attackers rely on la bels to calculate the gradient for perturbation, and exhibit low transferability to other structures and tasks. In this paper, we present a label-free white-box attack approach for ViT-based models that exhibits strong transferability to various black box models, including most ViT variants, CNNs, and MLPs, …
adversarial applications arxiv attackers challenges cs.cr cs.cv diversity feature low real transformers understanding vulnerability world
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Head of Security Operations
@ Canonical Ltd. | Home based - Americas, EMEA
Security Specialist
@ Lely | Maassluis, Netherlands
Senior Cyber Incident Response (Hybrid)
@ SmartDev | Cầu Giấy, Vietnam
Sr Security Engineer - Colombia
@ Nubank | Colombia, Bogota
Security Engineer, Investigations - i3
@ Meta | Menlo Park, CA | Washington, DC | Remote, US
Cyber Security Engineer
@ ASSYSTEM | Bridgwater, United Kingdom