Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 3964-3973 |
Number of pages | 10 |
ISBN (Electronic) | 9798350318920 |
DOIs | |
Publication status | Published - 2024 Jan 3 |
Event | 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 - Waikoloa, United States Duration: 2024 Jan 4 → 2024 Jan 8 |
Publication series
Name | Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 |
---|
Conference
Conference | 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 |
---|---|
Country/Territory | United States |
City | Waikoloa |
Period | 24/1/4 → 24/1/8 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition