EUVIMEDEUVIMED entdecken
Crossref

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

Hao Fang, Yixiang Qiu, Hongyao Yu, Wenbo Yu, Jiawei Kong, Baoli Chong, Bin Chen, Xuan Wang, Shu-Tao Xia, Ke Xu

International Journal of Computer Vision · 2026-10 · 134 (10)

DOI: 10.1007/s11263-026-03049-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 08.10.2026. Verfasst von Hao Fang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 165 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing access to the trained models, have emerged as a formidable privacy threat. Given a trained network, these attacks enable adversaries to reconstruct high-fidelity data that closely aligns with the private training samples, posing significant privacy concerns. Despite the rapid advances in the field, we lack a comprehensive and systematic overview of existing MI attacks and defenses. To fill this gap, this paper thoroughly investigates this realm and presents a holistic survey. Firstly, our work briefly reviews early MI studies on traditional machine learning scenarios. We then elaborately analyze and compare numerous recent attacks and defenses on Deep Neural Networks (DNNs) across multiple modalities and learning tasks. By meticulously analyzing their distinctive features, we summarize and classify these methods into different categories and provide a novel taxonomy. Finally, this paper discusses promising research directions and presents potential solutions to open issues. To facilitate further study on MI attacks and defenses, we have implemented an open-source model inversion toolbox on GitHub.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Fang, H., Qiu, Y., Yu, H., Yu, W., Kong, J., Chong, B., Chen, B., Wang, X., Xia, S., & Xu, K. (2026). Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses. International Journal of Computer Vision, 134(10). https://doi.org/10.1007/s11263-026-03049-x

Vancouver

Fang H, Qiu Y, Yu H, Yu W, Kong J, Chong B, et al. Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses. International Journal of Computer Vision. 2026;134(10). doi:10.1007/s11263-026-03049-x

BibTeX
@article{Fang2026,
  author = {Fang, Hao and Qiu, Yixiang and Yu, Hongyao and Yu, Wenbo and Kong, Jiawei and Chong, Baoli and Chen, Bin and Wang, Xuan and Xia, Shu-Tao and Xu, Ke},
  title = {Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  number = {10},
  doi = {10.1007/s11263-026-03049-x}
}
Kostenlos starten →