EUVIMEDEUVIMED entdecken
Crossref

FHE-EESI: A Lightweight Fully Homomorphic Encryption-Based End-Edge Collaborative Split Inference Framework

Haiyue Zhang, Yiming Liu, Jing Jin, Yanlu Li, Rui Meng, Jiaqi Wang, Siyuan Zheng

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 10657-10670

DOI: 10.1109/tccn.2026.3714807 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Haiyue Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, Beijing University of Posts and Telecommunications-China Mobile Communications Group Co., Ltd. Joint Institute..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

End-edge collaborative inference has emerged as an important trend for deploying deep learning applications on resource-constrained end devices. However, the continuous data interaction between end devices and edge server inevitably raises privacy concerns. Fully homomorphic encryption (FHE) provides a privacy-preserving solution by enabling inference directly on encrypted data, but deploying full FHE inference on the edge suffers from high latency. To address these issues, we propose FHE-EESI, an FHE-based end-edge collaborative split inference framework. In FHE-EESI, the end device executes the initial layers on plaintext, encrypts intermediate features using the residue number system Cheon-Kim-Kim-Song (RNS-CKKS) scheme, and transmits them to the edge server for the remaining FHE inference. To construct an FHE-compatible inference network and enable flexible partitionability, we adopt a stage-wise key management strategy and the Chebyshev polynomial approximation. Furthermore, considering dynamic channel conditions and heterogeneous computational capabilities, we design a dueling double deep Q-network (D3QN)-based dynamic split mechanism to adaptively determine the optimal split point. Experimental results on the CIFAR-10 dataset show that FHE-EESI achieves 83.3% inference accuracy and 183.1 s total latency, effectively providing privacy-preserving inference while maintaining inference efficiency.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Beijing University of Posts and Telecommunications-China Mobile Communications Group Co., Ltd. Joint Institute.
  • China Postdoctoral Science Foundation

Zitieren

APA

Zhang, H., Liu, Y., Jin, J., Li, Y., Meng, R., Wang, J., & Zheng, S. (2026). FHE-EESI: A Lightweight Fully Homomorphic Encryption-Based End-Edge Collaborative Split Inference Framework. IEEE Transactions on Cognitive Communications and Networking, 12, 10657-10670. https://doi.org/10.1109/tccn.2026.3714807

Vancouver

Zhang H, Liu Y, Jin J, Li Y, Meng R, Wang J, et al. FHE-EESI: A Lightweight Fully Homomorphic Encryption-Based End-Edge Collaborative Split Inference Framework. IEEE Transactions on Cognitive Communications and Networking. 2026;12:10657-10670. doi:10.1109/tccn.2026.3714807

BibTeX
@article{Zhang2026,
  author = {Zhang, Haiyue and Liu, Yiming and Jin, Jing and Li, Yanlu and Meng, Rui and Wang, Jiaqi and Zheng, Siyuan},
  title = {FHE-EESI: A Lightweight Fully Homomorphic Encryption-Based End-Edge Collaborative Split Inference Framework},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {10657--10670},
  doi = {10.1109/tccn.2026.3714807}
}
Kostenlos starten →