A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nikfam, Farzad, Casaburi, Raffaele, Marchisio, Alberto, Martina, Maurizio, Shafique, Muhammad
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908413538074624
author Nikfam, Farzad
Casaburi, Raffaele
Marchisio, Alberto
Martina, Maurizio
Shafique, Muhammad
author_facet Nikfam, Farzad
Casaburi, Raffaele
Marchisio, Alberto
Martina, Maurizio
Shafique, Muhammad
contents Machine learning (ML) is widely used today, especially through deep neural networks (DNNs), however, increasing computational load and resource requirements have led to cloud-based solutions. To address this problem, a new generation of networks called Spiking Neural Networks (SNN) has emerged, which mimic the behavior of the human brain to improve efficiency and reduce energy consumption. These networks often process large amounts of sensitive information, such as confidential data, and thus privacy issues arise. Homomorphic encryption (HE) offers a solution, allowing calculations to be performed on encrypted data without decrypting it. This research compares traditional DNNs and SNNs using the Brakerski/Fan-Vercauteren (BFV) encryption scheme. The LeNet-5 model, a widely-used convolutional architecture, is used for both DNN and SNN models based on the LeNet-5 architecture, and the networks are trained and compared using the FashionMNIST dataset. The results show that SNNs using HE achieve up to 40% higher accuracy than DNNs for low values of the plaintext modulus t, although their execution time is longer due to their time-coding nature with multiple time-steps.
format Preprint
id arxiv_https___arxiv_org_abs_2308_05636
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
Nikfam, Farzad
Casaburi, Raffaele
Marchisio, Alberto
Martina, Maurizio
Shafique, Muhammad
Cryptography and Security
Neural and Evolutionary Computing
Machine learning (ML) is widely used today, especially through deep neural networks (DNNs), however, increasing computational load and resource requirements have led to cloud-based solutions. To address this problem, a new generation of networks called Spiking Neural Networks (SNN) has emerged, which mimic the behavior of the human brain to improve efficiency and reduce energy consumption. These networks often process large amounts of sensitive information, such as confidential data, and thus privacy issues arise. Homomorphic encryption (HE) offers a solution, allowing calculations to be performed on encrypted data without decrypting it. This research compares traditional DNNs and SNNs using the Brakerski/Fan-Vercauteren (BFV) encryption scheme. The LeNet-5 model, a widely-used convolutional architecture, is used for both DNN and SNN models based on the LeNet-5 architecture, and the networks are trained and compared using the FashionMNIST dataset. The results show that SNNs using HE achieve up to 40% higher accuracy than DNNs for low values of the plaintext modulus t, although their execution time is longer due to their time-coding nature with multiple time-steps.
title A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
topic Cryptography and Security
Neural and Evolutionary Computing
url https://arxiv.org/abs/2308.05636