EUVIMEDEUVIMED entdecken
Crossref

Dual Protection for Image Privacy and Copyright via Traceable Adversarial Examples

Ming Li, Zhaoli Yang, Tao Wang, Yushu Zhang, Wenying Wen

IEEE Transactions on Circuits and Systems for Video Technology · 2024-12 · 34 (12) · 13401-13412

DOI: 10.1109/tcsvt.2024.3448351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-12. Verfasst von Ming Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Natural Science Foundation of China, Double Thousand Plan of Jiangxi Province, Outstanding Youth Fund Program of Jiangxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the uploading of massive personal images has increased the security risks, mainly including privacy breaches and copyright infringement. Adversarial examples provide a novel solution for protecting image privacy, as they can evade the detection by deep neural network (DNN)-based recognizers. However, the perturbations in the adversarial examples typically meaningless and therefore cannot be extracted as traceable information to support copyright protection. In this paper, we designed a dual protection scheme for image privacy and copyright via traceable adversarial examples. Specifically, a traceable adversarial model is proposed, which can be used to embed the invisible copyright information into images for copyright protection while fooling DNN-based recognizers for privacy protection. Inspired by the training method of generative adversarial networks (GANs), a new dynamic adversarial training strategy is designed, which allows our model for achieving stable multi-objective learning. Experimental results show that our scheme is exceptionally robust in the face of a variety of noise conditions and image processing methods, while exhibiting good model migration and defense robustness.

Förderung

  • Natural Science Foundation of China
  • Double Thousand Plan of Jiangxi Province
  • Outstanding Youth Fund Program of Jiangxi Province

Zitieren

APA

Li, M., Yang, Z., Wang, T., Zhang, Y., & Wen, W. (2024). Dual Protection for Image Privacy and Copyright via Traceable Adversarial Examples. IEEE Transactions on Circuits and Systems for Video Technology, 34(12), 13401-13412. https://doi.org/10.1109/tcsvt.2024.3448351

Vancouver

Li M, Yang Z, Wang T, Zhang Y, Wen W. Dual Protection for Image Privacy and Copyright via Traceable Adversarial Examples. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(12):13401-13412. doi:10.1109/tcsvt.2024.3448351

BibTeX
@article{Li2024,
  author = {Li, Ming and Yang, Zhaoli and Wang, Tao and Zhang, Yushu and Wen, Wenying},
  title = {Dual Protection for Image Privacy and Copyright via Traceable Adversarial Examples},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {12},
  pages = {13401--13412},
  doi = {10.1109/tcsvt.2024.3448351}
}
Kostenlos starten →