Paper ID: 2210.02502

On Adversarial Robustness of Deep Image Deblurring

Kanchana Vaishnavi Gandikota, Paramanand Chandramouli, Michael Moeller

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.

Submitted: Oct 5, 2022