Paper 2023/1428

XNET: A Real-Time Unified Secure Inference Framework Using Homomorphic Encryption

Hao Yang, Nanjing University of Aeronautics and Astronautics
Shiyu Shen, Fudan University
Siyang Jiang, Chinese University of Hong Kong
Lu Zhou, Nanjing University of Aeronautics and Astronautics
Wangchen Dai, Zhejiang Lab
Yunlei Zhao, Fudan University
Abstract

Homomorphic Encryption (HE) presents a promising solution to securing neural networks for Machine Learning as a Service (MLaaS). Despite its potential, the real-time applicability of current HE-based solutions remains a challenge, and the diversity in network structures often results in inefficient implementations and maintenance. To address these issues, we introduce a unified and compact network structure for real-time inference in convolutional neural networks based on HE. We further propose several optimization strategies, including an innovative compression and encoding technique and rearrangement in the pixel encoding sequence, enabling a highly efficient batched computation and reducing the demand for time-consuming HE operations. To further expedite computation, we propose a GPU acceleration engine to leverage the massive thread-level parallelism to speed up computations. We test our framework with the MNIST, Fashion-MNIST, and CIFAR-10 datasets, demonstrating accuracies of 99.14%, 90.8%, and 61.09%, respectively. Furthermore, our framework maintains a steady processing speed of 0.46 seconds on a single-thread CPU, and a brisk 31.862 milliseconds on an A100 GPU for all datasets. This represents an enhancement in speed more than 3000 times compared to pervious work, paving the way for future explorations in the realm of secure and real-time machine learning applications.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Preprint.
Keywords
Homomorphic EncryptionConvolutional Neural NetworkSecure inferenceGPU acceleration
Contact author(s)
crypto @ d4rk dev
shenshiyu21 @ m fudan edu cn
syjiang @ ie cuhk edu hk
lu zhou @ nuaa edu cn
w dai @ my cityu edu hk
ylzhao @ fudan edu cn
History
2023-09-24: approved
2023-09-21: received
See all versions
Short URL
https://ia.cr/2023/1428
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2023/1428,
      author = {Hao Yang and Shiyu Shen and Siyang Jiang and Lu Zhou and Wangchen Dai and Yunlei Zhao},
      title = {{XNET}: A Real-Time Unified Secure Inference Framework Using Homomorphic Encryption},
      howpublished = {Cryptology {ePrint} Archive, Paper 2023/1428},
      year = {2023},
      url = {https://eprint.iacr.org/2023/1428}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.