On Adversarial Robustness of Deep Image Deblurring
| Title: | On Adversarial Robustness of Deep Image Deblurring |
|---|---|
| Authors: | Gandikota, Kanchana Vaishnavi, Chandramouli, Paramanand, Moeller, Michael |
| Publication Year: | 2022 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing |
| More Details: | Recent approaches employ deep learning-based solutions for the recovery of a sharp image from its blurry observation. This paper introduces adversarial attacks against deep learning-based image deblurring methods and evaluates the robustness of these neural networks to untargeted and targeted attacks. We demonstrate that imperceptible distortion can significantly degrade the performance of state-of-the-art deblurring networks, even producing drastically different content in the output, indicating the strong need to include adversarially robust training not only in classification but also for image recovery. Comment: ICIP 2022 |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2210.02502 |
| Accession Number: | edsarx.2210.02502 |
| Database: | arXiv |
| Description not available. |