Adversarial purification for no-reference image-quality metrics: applicability study and new methods
This work addresses the under-researched area of defenses for IQA metrics against adversarial attacks, which is incremental as it adapts existing purification methods to a new domain.
The study tackled the problem of defending image quality assessment (IQA) metrics against adversarial attacks by testing the transferability of purification defenses from image classifiers, applying attacks on three IQA metrics and evaluating defenses using preprocessing techniques and neural networks.
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, compression, denoising, and modern neural network-based methods. Also, we address the challenge of assessing the efficacy of a defensive methodology by proposing ways to estimate output visual quality and the success of neutralizing attacks. Defences were tested against attack on three IQA metrics -- Linearity, MetaIQA and SPAQ. The code for attacks and defences is available at: (link is hidden for a blind review).