Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
This addresses the problem of unreliable IQA models in real-world systems like compression and streaming, offering a novel design-based approach rather than incremental data-driven defenses.
The paper tackles the vulnerability of Image Quality Assessment (IQA) models to adversarial perturbations by proposing a new architectural design that enforces orthogonal information flow and norm-preserving operations, resulting in a robust model that withstands attacks without adversarial training.
Image Quality Assessment (IQA) models are increasingly relied upon to evaluate image quality in real-world systems -- from compression and enhancement to generation and streaming. Yet their adoption brings a fundamental risk: these models are inherently unstable. Adversarial manipulations can easily fool them, inflating scores and undermining trust. Traditionally, such vulnerabilities are addressed through data-driven defenses -- adversarial retraining, regularization, or input purification. But what if this is the wrong lens? What if robustness in perceptual models is not something to learn but something to design? In this work, we propose a provocative idea: robustness as an architectural prior. Rather than training models to resist perturbations, we reshape their internal structure to suppress sensitivity from the ground up. We achieve this by enforcing orthogonal information flow, constraining the network to norm-preserving operations -- and further stabilizing the system through pruning and fine-tuning. The result is a robust IQA architecture that withstands adversarial attacks without requiring adversarial training or significant changes to the original model. This approach suggests a shift in perspective: from optimizing robustness through data to engineering it through design.