EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Face image de‐identification by feature space adversarial perturbation

Hanyu Xue, Bo Liu, Xin Yuan, Ming Ding, Tianqing Zhu

Concurrency and Computation: Practice and Experience · 28.02.2023 · 35 (5)

DOI: 10.1002/cpe.7554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 13.12.2022. Verfasst von Hanyu Xue und 4 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Privacy leakage in images attracts increasing concerns these days, as photos uploaded to large social platforms are usually not processed by proper privacy protection mechanisms. Moreover, with advanced artificial intelligence (AI) tools such as deep neural network (DNN), an adversary can detect people's identities and collect other sensitive personal information from images at an unprecedented scale. In this paper, we introduce a novel face image de‐identification framework using adversarial perturbations in the feature space. Manipulating the feature space vector ensures the good transferability of our framework. Moreover, the proposed feature space adversarial perturbation generation algorithm can successfully protect the identity‐related information while ensuring the other attributes remain similar. Finally, we conduct extensive experiments on two face image datasets to evaluate the performance of the proposed method. Our results show that the proposed method can generate real‐looking privacy‐preserving images efficiently. Although our framework has only been tested on two real‐life face image datasets, it can be easily extended to other types of images.

Zitieren

APA

Xue, H., Liu, B., Yuan, X., Ding, M., & Zhu, T. (2023). Face image de‐identification by feature space adversarial perturbation. Concurrency and Computation: Practice and Experience, 35(5). https://doi.org/10.1002/cpe.7554

Vancouver

Xue H, Liu B, Yuan X, Ding M, Zhu T. Face image de‐identification by feature space adversarial perturbation. Concurrency and Computation: Practice and Experience. 2023;35(5). doi:10.1002/cpe.7554

BibTeX
@article{Xue2023,
  author = {Xue, Hanyu and Liu, Bo and Yuan, Xin and Ding, Ming and Zhu, Tianqing},
  title = {Face image de‐identification by feature space adversarial perturbation},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2023},
  volume = {35},
  number = {5},
  doi = {10.1002/cpe.7554}
}
Kostenlos starten →