Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
This work addresses the critical concern of adversarial attacks on IQA metrics for researchers and practitioners in image processing, but it is incremental as it focuses on benchmarking existing methods rather than introducing new ones.
This paper tackled the problem of adversarial robustness in Image Quality Assessment (IQA) metrics by benchmarking 25 defense strategies against 14 adversarial attack algorithms, finding that no single defense universally outperforms others across all settings.
In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern. This paper presents a comprehensive benchmarking study of various defense mechanisms in response to the rise in adversarial attacks on IQA. We systematically evaluate 25 defense strategies, including adversarial purification, adversarial training, and certified robustness methods. We applied 14 adversarial attack algorithms of various types in both non-adaptive and adaptive settings and tested these defenses against them. We analyze the differences between defenses and their applicability to IQA tasks, considering that they should preserve IQA scores and image quality. The proposed benchmark aims to guide future developments and accepts submissions of new methods, with the latest results available online: https://videoprocessing.ai/benchmarks/iqa-defenses.html.