HEKAN:A new neural network for encrypted inference

Abstract

With the rapid development of neural network, the contradiction between improving the performance of network models and ensuring data privacy has become increasingly prominent. This paper proposes a novel neural network model, Homomorphic Encryption Kolmogorov-Arnold Networks(HEKAN), which deeply integrates Fully Homomorphic Encryption technology with Kolmogorov-Arnold Networks(KAN). Our salient advantage resides in the successful implementation of a neural network model, herein referred to as the HEKAN model, which takes advantage of the KAN model’s few parameters, high accuracy, and strong characterization capabilities to make the cryptographic inference process more interpretable, and faster, also enhances security and efficiency in inference process, thereby laying a robust foundation for secure applications within the realm of artificial intelligence.

Authors 6

1. Yuwei Xu

   Xi'an University of Technology

   Affiliation as printed

   Xi’an University of Technology,Faculty of Automation and Information Engineering,Xi’an,China

2. Han Liu

   Xi'an University of Technology

   Affiliation as printed

   Xi’an University of Technology,Faculty of Automation and Information Engineering,Xi’an,China

3. Zhongyu Hu Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands

4. Xiaodong Li

   Beijing Electronic Science and Technology Institute

   Affiliation as printed

   Beijing Electronic Science and Technology Institute,Department of Cyberspace Security,Beijing,China

5. Yimeng Dou

   Beijing Electronic Science and Technology Institute

   Affiliation as printed

   Beijing Electronic Science and Technology Institute,Department of Cyberspace Security,Beijing,China

6. Shaofei Xu

   Beijing Electronic Science and Technology Institute

   Affiliation as printed

   Beijing Electronic Science and Technology Institute,Department of Cyberspace Security,Beijing,China