从频谱视角探究视觉Transformer的对抗鲁棒性
Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective
AI总结：
该研究从频谱视角探究视觉Transformer的对抗鲁棒性，构建可实现空间域与频谱域攻击的框架，发现Transformer更依赖相位和低频信息，比CNNs更易受频率选择性攻击，为其特性与鲁棒性研究提供新见解。
摘要：
视觉Transformer已成为图像分类任务的强大工具，性能超越卷积神经网络（CNNs）。近期，众多研究者试图理解Transformer对抗攻击的鲁棒性，但以往研究仅聚焦于空间域的扰动。本文提出一个全新视角，探究Transformer在频谱域中对抗频率选择性扰动的鲁棒性。为便于两个域之间的比较，本文构建了一个攻击框架，作为在空间域和频谱域对图像实施攻击的灵活工具。实验表明，Transformer更依赖相位和低频信息，这使得它们比CNNs更易受到频率选择性攻击。本研究为理解Transformer的特性与对抗鲁棒性提供了新的见解。
英文摘要：
The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robustness of Transformers against adversarial attacks. However, previous researches have focused solely on perturbations in the spatial domain. This paper proposes an additional perspective that explores the adversarial robustness of Transformers against frequency-selective perturbations in the spectral domain. To facilitate comparison between these two domains, an attack framework is formulated as a flexible tool for implementing attacks on images in the spatial and spectral domains. The experiments reveal that Transformers rely more on phase and low frequency information, which can render them more vulnerable to frequency-selective attacks than CNNs. This work offers new insights into the properties and adversarial robustness of Transformers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
