Deep Image Destruction: Vulnerability of Deep Image-to-Image Models against Adversarial Attacks
Authors:
- 21 August 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1287-1293
Abstract
Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated. However, such an issue has not been thoroughly studied for image-to-image tasks that take an input image and generate an output image (e.g., colorization, denoising, deblurring, etc.) This paper presents comprehensive investigations into the vulnerability of deep image-to-image models to adversarial attacks. For five popular image-to-image tasks, 16 deep models are analyzed from various standpoints such as output quality degradation due to attacks, transferability of adversarial examples across different tasks, and characteristics of perturbations. We show that unlike image classification tasks, the performance degradation on image-to-image tasks largely differs depending on various factors, e.g., attack methods and task objectives. In addition, we analyze the effectiveness of conventional defense methods used for classification models in improving the robustness of the image-to-image models.Keywords
All Related Versions
Funding Information
- Yonsei University
This publication has 18 references indexed in Scilit:
- When Deep Fool Meets Deep Prior2018
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- Is Robustness the Cost of Accuracy? – A Comprehensive Study on the Robustness of 18 Deep Image Classification Models2018
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks2018
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2017
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- Deep Residual Learning for Image Recognition2016