EUVIMEDEUVIMED entdecken
Crossref

Adaptive Generative Model Inversion Attacks in Edge–Cloud Collaborative Inference Systems

Haoyu Liu, Yuwen Chen, Zhen Yang

IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 13846-13862

DOI: 10.1109/tmc.2026.3673987 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Haoyu Liu und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Major Research Plan of National Natural Science Foundation of China, National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Previous model inversion attacks in collaborative inference systems have only been demonstrated on simple models. They failed to produce convincing results on large models or large images. To improve the quality of the model inversion attack, two adaptive generative model inversion attacks are proposed. First, the distributional prior of the publicly available pre-trained Generative Adversarial Nets are used to guide the reconstruction process. Second, previous works only search the latent space of the pre-trained GAN. However, the pre-trained generative model and the target model are trained on different datasets. The distribution shifts of the datasets can lead to inevitable reconstruction errors. To handle the distribution shifts, the pre-trained generative model will be fine-tuned for target instances in the proposed adaptive generative model inversion attack. As a result, the proposed attacks can better handle the distribution shifts. And there is no need to train a separate image prior for each target model. The generators can be used to attack different models trained on different datasets within the same domain. Our extensive experiments demonstrate that the proposed attack achieves up to a 25.7% improvement in PSNR and a 26.4% improvement in SSIM compared to previous methods.

Förderung

  • National Natural Science Foundation of China
  • Major Research Plan of National Natural Science Foundation of China
  • National Key R&D Program of China
  • R& D Program of Beijing Municipal Education Commission
  • “Engineering Research Center of Intelligent Perception and Autonomous Control, Ministry of Education”

Zitieren

APA

Liu, H., Chen, Y., & Yang, Z. (2026). Adaptive Generative Model Inversion Attacks in Edge–Cloud Collaborative Inference Systems. IEEE Transactions on Mobile Computing, 25(9), 13846-13862. https://doi.org/10.1109/tmc.2026.3673987

Vancouver

Liu H, Chen Y, Yang Z. Adaptive Generative Model Inversion Attacks in Edge–Cloud Collaborative Inference Systems. IEEE Transactions on Mobile Computing. 2026;25(9):13846-13862. doi:10.1109/tmc.2026.3673987

BibTeX
@article{Liu2026,
  author = {Liu, Haoyu and Chen, Yuwen and Yang, Zhen},
  title = {Adaptive Generative Model Inversion Attacks in Edge–Cloud Collaborative Inference Systems},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {9},
  pages = {13846--13862},
  doi = {10.1109/tmc.2026.3673987}
}
Kostenlos starten →