On the Generation of Adversarial Samples for Image Quality Assessment

Abstract

We study the generation of adversarial samples to test, assess, and improve deep learning-based image quality assessment (IQA) algorithms. This is important since social media platforms and other providers rely on IQA models to monitor the content they ingest, and to control the quality of pictures that are shared. Unfortunately, IQA models based on deep learning are vulnerable to adversarial attacks. We created an adversarial sample image generation tool that generates aggressive adversarial samples having good attack success rates. We hope that it can be used to help IQA researchers assess and improve the robustness of IQA.

Keywords: Adversarial example, Deep learning, Image quality assessment