A legendre-kan encryption reasoning method based on mode component homomorphism

By constructing the Legendre-KAN network and utilizing GPU parallel computing, combined with the modular component homomorphic algorithm, the problem of low computational efficiency of homomorphic encryption technology in deep learning inference is solved, achieving efficient and secure data privacy protection and meeting the high-precision computational needs of deep learning models.

CN120449181BActive Publication Date: 2025-11-25BEIJING ELECTRONICS SCI & TECH INST
1 Cites 0 Cited by

Patent Information

Application Number
CN202510513100.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-04-23
Publication Date
2025-11-25
Estimated Expiration
2045-04-23

AI Technical Summary

Technical Problem

Existing homomorphic encryption technologies suffer from low computational efficiency and insufficient support for floating-point operations during deep learning inference, failing to meet all the computational needs of neural networks. Furthermore, traditional algorithms are inefficient and cannot meet the demands for high efficiency and real-time performance in real-world scenarios.

Method used

We adopt the Legendre-KAN cryptographic inference method based on modular component homomorphism. By constructing the Legendre-KAN network and utilizing GPU parallel computing strategy, we combine the modular component homomorphism algorithm for cryptographic inference. This method supports floating-point operations and high-precision calculations, avoiding the computational complexity and nonlinearity defects of traditional methods.

Benefits of technology

It improves computational efficiency, supports high-precision floating-point operations, reduces computational costs and storage overhead, and ensures the security and efficiency of data privacy in an encrypted environment.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a kind of based on module component homomorphism's Legendre-KAN encryption reasoning method, it is related to information security technical field, including: step 1: based on Legendre polynomial's KAN structure constructs Legendre-KAN network;Step 2: image sample set is collected to the Legendre-KAN network training obtains Legendre-KAN model;Step 3: to be predicted image is encrypted, obtains ciphertext data;Step 4: in GPU, utilizes Legendre-KAN model and uses module component homomorphism algorithm to ciphertext data and carries out parallel reasoning, obtains encryption result;Step 5: to encryption result is decrypted and obtains image prediction result.The application can make the data in entire reasoning process always in encrypted state, effectively avoid privacy leakage, and can improve model reasoning efficiency, accelerates data reasoning process.
Need to check novelty before this filing date? Find Prior Art