Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment

TL;DR

This paper introduces a provably robust no-reference image quality assessment method using median smoothing and denoising, enhancing reliability against adversarial attacks with theoretical guarantees.

Contribution

It proposes a novel stochastic BIQA approach combining median smoothing with denoising, providing certified robustness and improved correlation scores over prior methods.

Findings

Superior SROCC and PLCC scores on three datasets

Maintains comparable certified guarantees to existing methods

Enhances robustness of IQA metrics against adversarial attacks

Abstract

Most modern No-Reference Image-Quality Assessment (NR-IQA) metrics are based on neural networks vulnerable to adversarial attacks. Attacks on such metrics lead to incorrect image/video quality predictions, which poses significant risks, especially in public benchmarks. Developers of image processing algorithms may unfairly increase the score of a target IQA metric without improving the actual quality of the adversarial image. Although some empirical defenses for IQA metrics were proposed, they do not provide theoretical guarantees and may be vulnerable to adaptive attacks. This work focuses on developing a provably robust no-reference IQA metric. Our method is based on Median Smoothing (MS) combined with an additional convolution denoiser with ranking loss to improve the SROCC and PLCC scores of the defended IQA metric. Compared with two prior methods on three datasets, our method exhibited superior SROCC and PLCC scores while maintaining comparable certified guarantees.