Low-rank matrix recovery with total generalized variation for defending adversarial examples  

作　　者：Wen LI Hengyou WANG Lianzhi HUO Qiang HE Linlin CHEN Zhiquan HE Wing W.Y.Ng 

机构地区：[1]School of Science,Beijing University of Civil Engineering and Architecture,Beijing 100044,China [2]School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,China [3]Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China [4]Guangdong Key Laboratory of Intelligent Information Processing,Shenzhen 518060,China [5]Institute of Big Data Modeling and Technology,Beijing University of Civil Engineering and Architecture,Beijing 100044,China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2024年第3期432-445,共14页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Natural Science Foundation of China(No.62072024);the Outstanding Youth Program of Beijing University of Civil Engineering and Architecture,China(No.JDJQ20220805);the Shenzhen Stability Support General Project(Type A),China(No.20200826104014001)。

摘　　要：Low-rank matrix decomposition with first-order total variation(TV)regularization exhibits excellent performance in exploration of image structure.Taking advantage of its excellent performance in image denoising,we apply it to improve the robustness of deep neural networks.However,although TV regularization can improve the robustness of the model,it reduces the accuracy of normal samples due to its over-smoothing.In our work,we develop a new low-rank matrix recovery model,called LRTGV,which incorporates total generalized variation(TGV)regularization into the reweighted low-rank matrix recovery model.In the proposed model,TGV is used to better reconstruct texture information without over-smoothing.The reweighted nuclear norm and Li-norm can enhance the global structure information.Thus,the proposed LRTGV can destroy the structure of adversarial noise while re-enhancing the global structure and local texture of the image.To solve the challenging optimal model issue,we propose an algorithm based on the alternating direction method of multipliers.Experimental results show that the proposed algorithm has a certain defense capability against black-box attacks,and outperforms state-of-the-art low-rank matrix recovery methods in image restoration.

关 键 词：Total generalized variation Low-rank matrix Alternating direction method of multipliers Adversarial example 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]