Research map / Adversarial robustness and security / Black-box and transfer attacks
Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes gradient-normalization scaling and high-frequency adaptation to improve transferable black-box adversarial attacks on Vision Transformers.
Problem
Transferable adversarial attacks crafted on surrogate models often transfer poorly to Vision Transformers, which are vulnerable to adversarial samples and deployed in security-sensitive settings.
Approach
Combines gradient normalization scaling with high-frequency adaptation to craft more transferable adversarial samples against ViTs in a black-box setting, without accessing target model parameters.
Closest papers by meaning
- Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning (NeurIPS 2024 · similarity 0.94)
- Improving the Adversarial Transferability of Vision Transformers with Virtual Dense Connection (AAAI 2024 · similarity 0.93)
- Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability (NeurIPS 2025 · similarity 0.92)
- Attacking Transformers with Feature Diversity Adversarial Perturbation (AAAI 2024 · similarity 0.92)
- Towards Understanding and Improving Adversarial Robustness of Vision Transformers (CVPR 2024 · similarity 0.91)
- Enhancing Adversarial Transferability with Adversarial Weight Tuning (AAAI 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.