EUVIMEDEUVIMED entdecken
Crossref

TEESlice : Protecting Sensitive Neural Network Models in Trusted Execution Environments when Attackers Have Pre-Trained Models

Ding Li, Ziqi Zhang, Mengyu Yao, Yifeng Cai, Yao Guo, Xiangqun Chen

ACM Transactions on Software Engineering and Methodology · 31.07.2025 · 34 (6) · 1-49

DOI: 10.1145/3707453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, 2025-07. Verfasst von Ding Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 163 Literaturangaben. Gefördert von: National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trusted Execution Environments (TEEs) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN’s computation speed but widely available commercial GPUs usually lack security protection. To this end, scholars introduce TEE-Shielded DNN Partition (TSDP), a method that protects privacy-sensitive weights within TEEs and offloads insensitive weights to GPUs. Nevertheless, current methods do not consider the presence of a knowledgeable adversary who can access abundant publicly available pre-trained models and datasets. This article investigates the security of the existing methods against such a knowledgeable adversary and reveals their inability to fulfill their security promises. Consequently, we introduce a novel partition before training strategy, which effectively separates privacy-sensitive weights from other components of the model. Our evaluation demonstrates that our approach can offer full model protection with a computational cost reduced by a factor of 10. In addition to traditional CNN models, we also demonstrate the scalability to large language models. Our approach can compress the private functionalities of the large language model to lightweight slices and achieve the same level of protection as the shielding-whole-model baseline.

Förderung

  • National Science and Technology Major Project

Zitieren

APA

Li, D., Zhang, Z., Yao, M., Cai, Y., Guo, Y., & Chen, X. (2025). TEESlice : Protecting Sensitive Neural Network Models in Trusted Execution Environments when Attackers Have Pre-Trained Models. ACM Transactions on Software Engineering and Methodology, 34(6), 1-49. https://doi.org/10.1145/3707453

Vancouver

Li D, Zhang Z, Yao M, Cai Y, Guo Y, Chen X. TEESlice : Protecting Sensitive Neural Network Models in Trusted Execution Environments when Attackers Have Pre-Trained Models. ACM Transactions on Software Engineering and Methodology. 2025;34(6):1-49. doi:10.1145/3707453

BibTeX
@article{Li2025,
  author = {Li, Ding and Zhang, Ziqi and Yao, Mengyu and Cai, Yifeng and Guo, Yao and Chen, Xiangqun},
  title = {TEESlice : Protecting Sensitive Neural Network Models in Trusted Execution Environments when Attackers Have Pre-Trained Models},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2025},
  volume = {34},
  number = {6},
  pages = {1--49},
  doi = {10.1145/3707453}
}
Kostenlos starten →