EUVIMEDEUVIMED entdecken
Crossref

East: Efficient and Accurate Secure Inference Framework for Transformer

Yuanchao Ding, Hua Guo, Yewei Guan, Weixin Liu, Jiarong Huo, Zhenyu Guan, Xiyong Zhang

IEEE Transactions on Services Computing · 2025-07 · 18 (4) · 2038-2046

DOI: 10.1109/tsc.2025.3577491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2025-07. Verfasst von Yuanchao Ding und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 34 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformer has been successfully used in practical applications due to its powerful advantages. However, users’ input is leaked to the model provider during the service. With people’s attention to privacy, privacy-preserving Transformer inference is on the demand of such services. Secure protocols for non-linear functions are crucial in privacy-preserving Transformer inference, which are not well studied. Thus, designing practical secure protocols for non-linear functions is hard but significant to model performance. In this work, we propose a framework East to enable efficient and accurate secure Transformer inference. First, we propose a new oblivious piecewise polynomial evaluation algorithm and apply it to the activation functions, which reduces the runtime and communication of GELU by over 1.5× and 2.5×, compared to prior arts. Second, the secure protocols for softmax and layer normalization are carefully designed to faithfully maintain the desired functionality. Third, several optimizations are conducted in detail to enhance the overall efficiency. We applied East to BERT and the results show that the inference accuracy remains consistent with the plaintext inference without fine-tuning. Compared to Iron, we achieve about 1.8× lower communication within 1.2× lower runtime.

Zitieren

APA

Ding, Y., Guo, H., Guan, Y., Liu, W., Huo, J., Guan, Z., & Zhang, X. (2025). East: Efficient and Accurate Secure Inference Framework for Transformer. IEEE Transactions on Services Computing, 18(4), 2038-2046. https://doi.org/10.1109/tsc.2025.3577491

Vancouver

Ding Y, Guo H, Guan Y, Liu W, Huo J, Guan Z, et al. East: Efficient and Accurate Secure Inference Framework for Transformer. IEEE Transactions on Services Computing. 2025;18(4):2038-2046. doi:10.1109/tsc.2025.3577491

BibTeX
@article{Ding2025,
  author = {Ding, Yuanchao and Guo, Hua and Guan, Yewei and Liu, Weixin and Huo, Jiarong and Guan, Zhenyu and Zhang, Xiyong},
  title = {East: Efficient and Accurate Secure Inference Framework for Transformer},
  journal = {IEEE Transactions on Services Computing},
  year = {2025},
  volume = {18},
  number = {4},
  pages = {2038--2046},
  doi = {10.1109/tsc.2025.3577491}
}
Kostenlos starten →