Secure Video Quality Assessment Resisting Adversarial Attacks

TL;DR

This paper introduces SecureVQA, a novel video quality assessment model designed to resist adversarial attacks by employing spatial and temporal defense mechanisms, achieving high security without sacrificing assessment accuracy.

Contribution

The paper proposes a security-oriented VQA framework with innovative defense strategies, including spatial grid sampling and pixel-wise randomization, to enhance robustness against adversarial attacks.

Findings

SecureVQA outperforms existing models in security benchmarks.

The proposed defenses effectively neutralize adversarial perturbations.

SecureVQA maintains competitive accuracy in video quality assessment.

Abstract

The exponential surge in video traffic has intensified the imperative for Video Quality Assessment (VQA). Leveraging cutting-edge architectures, current VQA models have achieved human-comparable accuracy. However, recent studies have revealed the vulnerability of existing VQA models against adversarial attacks. To establish a reliable and practical assessment system, a secure VQA model capable of resisting such malicious attacks is urgently demanded. Unfortunately, no attempt has been made to explore this issue. This paper first attempts to investigate general adversarial defense principles, aiming at endowing existing VQA models with security. Specifically, we first introduce random spatial grid sampling on the video frame for intra-frame defense. Then, we design pixel-wise randomization through a guardian map, globally neutralizing adversarial perturbations. Meanwhile, we extract temporal information from the video sequence as compensation for inter-frame defense. Building upon these principles, we present a novel VQA framework from the security-oriented perspective, termed SecureVQA. Extensive experiments indicate that SecureVQA sets a new benchmark in security while achieving competitive VQA performance compared with state-of-the-art models. Ablation studies delve deeper into analyzing the principles of SecureVQA, demonstrating their generalization and contributions to the security of leading VQA models.