Efficient Artificial Intelligence With Novel Matrix Transformations and Homomorphic Encryption

Quoc Bao Phan, Tuy Tan Nguyen

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

This paper addresses the challenges of data privacy and computational efficiency in artificial intelligence (AI) models by proposing a novel hybrid model that combines homomorphic encryption (HE) with AI to enhance security while maintaining learning accuracy. The novelty of our model lies in the introduction of a new matrix transformation technique that ensures compatibility with both HE algorithms and AI model weight matrices, significantly improving computational efficiency. Furthermore, we present a first-of-its-kind mathematical proof of convergence for integrating HE into AI models using the adaptive moment estimation optimization algorithm. The effectiveness and practicality of our approach for training on encrypted data are showcased through comprehensive evaluations of well-known datasets for air pollution forecasting and forest fire detection. These successful results demonstrate high model performance, with nearly 1 R-squared for air pollution forecasting and 99% accuracy for forest fire detection. Additionally, our approach achieves a reduction of up to 90% in data storage and a tenfold increase in speed compared to models that do not use the matrix transformation method. Our primary contribution lies in enhancing the security, efficiency, and dependability of AI models, particularly when dealing with sensitive data.

Original languageEnglish (US)
Pages (from-to)717-728
Number of pages12
JournalIEEE Journal on Emerging and Selected Topics in Circuits and Systems
Volume14
Issue number4
DOIs
StatePublished - 2024
Externally publishedYes

Keywords

  • Artificial intelligence
  • convergence analysis
  • homomorphic encryption
  • matrix transformation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Efficient Artificial Intelligence With Novel Matrix Transformations and Homomorphic Encryption'. Together they form a unique fingerprint.

Cite this