Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Homomorphic Encryption for Machine Learning and Artificial Intelligence Applications

Technical Report ·
DOI:https://doi.org/10.2172/1886256· OSTI ID:1886256
 [1];  [2];  [3]
  1. Argonne National Lab. (ANL), Argonne, IL (United States); Illinois Institute of Technology, Chicago, IL (United States)
  2. Illinois Institute of Technology, Chicago, IL (United States)
  3. Argonne National Lab. (ANL), Argonne, IL (United States)

Third-party and expert analysis is a cost-effective solution for solving specialized problems or processing large datasets related to reactor structural health monitoring and nondestructive evaluation. However, when handling proprietary information, third-party and expert analysts pose a privacy risk. To address this challenge, Homomorphic Encryption (HE) permits arithmetic operations on encrypted data without exposing the underlying data. Implementations of Machine Learning (ML) and Artificial Intelligence (AI) algorithms using HE greatly enhances the capabilities of third-party analysts while maintaining a low security risk. This paper details current success in applying Principal Component Analysis (PCA) and Fully Connected Neural Networks (NN) using the Microsoft SEAL implementation of the popular CKKS Fully Homomorphic Encryption (FHE) algorithm. The MNIST Handwritten Dataset is analyzed as a proof-of-concept demonstration of the implementations.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE), Nuclear Energy Enabling Technologies (NEET)
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1886256
Report Number(s):
ANL/NSE-22/54; 177974
Country of Publication:
United States
Language:
English

Similar Records

Privacy-Preserving Artificial Intelligence on Edge Devices: A Homomorphic Encryption Approach
Conference · Mon Oct 14 00:00:00 EDT 2024 · OSTI ID:2526242

End-to-End Encryption for Cyber-Physical Systems Using Fully Homomorphic Encryption
Conference · Mon Apr 29 00:00:00 EDT 2024 · OSTI ID:2439933

Fully Homomorphic Encryption
Software · Thu Jun 19 20:00:00 EDT 2025 · OSTI ID:code-160029