Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks
Abstract
Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many image processing applications. This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion in the attacked low-resolution images. It is demonstrated that state-of-the-art deep super-resolution methods are highly vulnerable to adversarial attacks. Different levels of robustness of different methods are analyzed theoretically and experimentally. We also present analysis on transferability of attacks, and feasibility of targeted attacks and universal attacks.
Cite
Text
Choi et al. "Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00039Markdown
[Choi et al. "Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/choi2019iccv-evaluating/) doi:10.1109/ICCV.2019.00039BibTeX
@inproceedings{choi2019iccv-evaluating,
title = {{Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks}},
author = {Choi, Jun-Ho and Zhang, Huan and Kim, Jun-Hyuk and Hsieh, Cho-Jui and Lee, Jong-Seok},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00039},
url = {https://mlanthology.org/iccv/2019/choi2019iccv-evaluating/}
}