Removing Adversarial Noise via Low-Rank Completion of High-Sensitivity Points
- 10 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 6485-6497
Abstract
Deep neural networks are fragile under adversarial attacks. In this work, we propose to develop a new defense method based on image restoration to remove adversarial attack noise. Using the gradient information back-propagated over the network to the input image, we identify high-sensitivity keypoints which have significant contributions to the image classification performance. We then partition the image pixels into the two groups: high-sensitivity and low-sensitivity points. For low-sensitivity pixels, we use a total variation (TV) norm-based image smoothing method to remove adversarial attack noise. For those high-sensitivity keypoints, we develop a structure-preserving low-rank image completion method. Based on matrix analysis and optimization, we derive an iterative solution for this optimization problem. Our extensive experimental results on the CIFAR-10, SVHN, and Tiny-ImageNet datasets have demonstrated that our method significantly outperforms other defense methods which are based on image de-noising or restoration, especially under powerful adversarial attacks.Keywords
Funding Information
- National Natural Science Foundation of China (62072024, 61971290)
- Project of Beijing Advanced Innovation Center for Future Urban Design, Beijing University of Civil Engineering and Architecture (UDC2019033324)
- Fundamental Research Funds for Municipal Universities of Beijing University of Civil Engineering and Architecture (X20084)
- National Science Foundation (1646162, 1647213, 1646065)
This publication has 22 references indexed in Scilit:
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Rank adaptive atomic decomposition for low-rank matrix completion and its application on image recoveryNeurocomputing, 2014
- Reweighted Low-Rank Matrix Recovery and its Application in Image RestorationIEEE Transactions on Cybernetics, 2014
- Robust Recovery of Corrupted Low-RankMatrix by Implicit RegularizersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Matrix Completion With NoiseProceedings of the IEEE, 2010
- Fixed point and Bregman iterative methods for matrix rank minimizationMathematical Programming, 2009
- Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring ProblemsIEEE Transactions on Image Processing, 2009
- Exact Matrix Completion via Convex OptimizationFoundations of Computational Mathematics, 2009
- Enhancing Sparsity by Reweighted ℓ 1 MinimizationJournal of Fourier Analysis and Applications, 2008