Understanding the adversarial robustness of deep learning-based single-pixel imaging
Authors:
- Zhenyu LiangZLZhenyu Liang
- Lipeng WangLWLipeng Wang
- Yunfeng DiaoYDYunfeng Diao
- Yangyang WangYWYangyang Wang
- Hua MuHMHua Mu
- Lei ZuoLZLei Zuo
- Haoqi GaoHGHaoqi Gao
- Zhaoxin FanZFZhaoxin Fan
- Xing YangXYXing Yang
- 10 October 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 172
Abstract
No abstract availableFunding Information
- National University of Defense Technology (ZK24-47)
- National Natural Science Foundation of China (62302139)
This publication has 11 references indexed in Scilit:
- A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and RethinkingInternational Journal of Computer Vision, 2024
- A compressive hyperspectral video imaging system using a single-pixel detectorNature Communications, 2024
- Fooling the Image Dehazing Models by First Order GradientIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Learning-based adaptive under-sampling for Fourier single-pixel imagingOptics Letters, 2023
- Adversarial Attacks Against Face Recognition: A Comprehensive StudyIEEE Access, 2021
- Image Compressed Sensing Using Convolutional Neural NetworkIEEE Transactions on Image Processing, 2019
- Experimental X-Ray Ghost ImagingPhysical Review Letters, 2016
- Single-pixel imaging by means of Fourier spectrum acquisitionNature Communications, 2015
- Ghost imaging lidar via sparsity constraintsApplied Physics Letters, 2012
- Compressive ghost imagingApplied Physics Letters, 2009