Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 12538-12546
Abstract
No abstract availableAll Related Versions
Funding Information
- Ministry of Economic Development of the Russian Federation (000000C313925P4G0002)
This publication has 15 references indexed in Scilit:
- Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization2024
- Pruning Adversarially Robust Neural Networks without Adversarial Examples2022
- Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks2022
- On the Effect of Pruning on Adversarial Robustness2021
- Discriminative Layer Pruning for Convolutional Neural NetworksIEEE Journal of Selected Topics in Signal 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
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Universal Adversarial Perturbations2017
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004