Invertible Privacy-Preserving Adversarial Reconstruction for Image Compressed Sensing
Sensors · 29.03.2023 · 23 (7) · 3575
DOI: 10.3390/s23073575 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2023. Verfasst von Di Xiao und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science, Chongqing University, Chongqing 400044, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Project Supported by Graduate Student Research and Innovation Foundation of Chongqing, China, Graduate Student Research and Innovation Foundation of Chongqing, China.
Abstract (Originalsprache)
Since the advent of compressed sensing (CS), many reconstruction algorithms have been proposed, most of which are devoted to reconstructing images with better visual quality. However, higher-quality images tend to reveal more sensitive information in machine recognition tasks. In this paper, we propose a novel invertible privacy-preserving adversarial reconstruction method for image CS. While optimizing the quality, the reconstructed images are made to be adversarial samples at the moment of generation. For semi-authorized users, they can only obtain the adversarial reconstructed images, which provide little information for machine recognition or training deep models. For authorized users, they can reverse adversarial reconstructed images to clean samples with an additional restoration network. Experimental results show that while keeping good visual quality for both types of reconstructed images, the proposed scheme can provide semi-authorized users with adversarial reconstructed images with a very low recognizable rate, and allow authorized users to further recover sanitized reconstructed images with recognition performance approximating that of the traditional CS.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science, Chongqing University, Chongqing 400044, China.
ORCID-Profile: Di Xiao
Förderung
- National Natural Science Foundation of China
- Project Supported by Graduate Student Research and Innovation Foundation of Chongqing, China
- Graduate Student Research and Innovation Foundation of Chongqing, China
Zitieren
APA
Xiao, D., Li, Y., & Li, M. (2023). Invertible Privacy-Preserving Adversarial Reconstruction for Image Compressed Sensing. Sensors, 23(7), 3575. https://doi.org/10.3390/s23073575
Vancouver
Xiao D, Li Y, Li M. Invertible Privacy-Preserving Adversarial Reconstruction for Image Compressed Sensing. Sensors. 2023;23(7):3575. doi:10.3390/s23073575
BibTeX
@article{Xiao2023,
author = {Xiao, Di and Li, Yue and Li, Min},
title = {Invertible Privacy-Preserving Adversarial Reconstruction for Image Compressed Sensing},
journal = {Sensors},
year = {2023},
volume = {23},
number = {7},
pages = {3575},
doi = {10.3390/s23073575}
}
EUVIMED