English

On Adversarial Robustness of Deep Image Deblurring

Computer Vision and Pattern Recognition 2022-10-07 v1 Image and Video Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2210.02502,
  title  = {On Adversarial Robustness of Deep Image Deblurring},
  author = {Kanchana Vaishnavi Gandikota and Paramanand Chandramouli and Michael Moeller},
  journal= {arXiv preprint arXiv:2210.02502},
  year   = {2022}
}

Comments

ICIP 2022

R2 v1 2026-06-28T02:53:01.843Z