Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Increasing the Robustness of Image Quality Assessment Models Through Adversarial TrainingTechnologies, 2024
- Adversarial Attacks Against Blind Image Quality Assessment Models2022
- Perceptual Attacks of No-Reference Image Quality Models with Human-In-The-Loop2022
- Image Quality Assessment: Unifying Structure and Texture SimilarityIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Discriminative Layer Pruning for Convolutional Neural NetworksIEEE Journal of Selected Topics in Signal Processing, 2020
- KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality AssessmentIEEE Transactions on Image Processing, 2020
- Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural NetworkIEEE Transactions on Circuits and Systems for Video Technology, 2018
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learningNeural Networks, 2018
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004