Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

2024, Volume 25, Issue 3

Abstract

Keywords

Related Research

Back to Top

Frontiers of Information Technology & Electronic Engineering >> 2024, Volume 25, Issue 3 doi: 10.1631/FITEE.2300017

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

Affiliation(s): School of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, China; School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China; Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen 518060, China; Institute of Big Data Modeling and Technology, Beijing University of Civil Engineering and Architecture, Beijing 100044, China; less

Received: 2023-01-09 Accepted: 2024-03-25 Available online: 2024-03-25
HTML0 PDF 0 Collect 0

Next Previous

Abstract

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 recovery model, called LRTGV, which incorporates (TGV) regularization into the reweighted recovery model. In the proposed model, TGV is used to better reconstruct texture information without over-smoothing. The reweighted nuclear norm and -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 . Experimental results show that the proposed algorithm has a certain defense capability against black-box attacks, and outperforms state-of-the-art recovery methods in image restoration.

Related Research