Adversarial purification for no-reference image-quality metrics: applicability study and new methods

arXiv:2404.06957v1 Announce Type: new
Abstract: Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial purification defences from image classifiers to IQA methods. In this paper, we apply several widespread attacks on IQA models and examine the success of the defences against them. The purification methodologies covered different preprocessing techniques, including geometrical transformations, …

abstract adversarial adversarial attacks aim arxiv attacks begun case check classifiers cs.ai cs.cv image image-quality metrics quality reference study type