Privacy-Preserving Spiking Neural Networks: A Deep Dive into Encryption Parameter Optimisation

TL;DR

This paper presents BioEncryptSNN, a novel spiking neural network-based encryption framework that enhances data privacy and security while offering faster encryption and decryption compared to traditional cryptographic algorithms.

Contribution

It introduces a new encryption-decryption framework using SNNs that optimizes parameters for secure, noise-resilient data protection and demonstrates superior performance over standard cryptographic methods.

Findings

BioEncryptSNN preserves data integrity during encryption.

Achieves up to 4.1x faster encryption/decryption than AES-128.

Demonstrates scalability across different cipher types.

Abstract

Deep learning is widely applied to modern problems through neural networks, but the growing computational and energy demands of these models have driven interest in more efficient approaches. Spiking Neural Networks (SNNs), the third generation of neural networks, mimic the brain's event-driven behaviour, offering improved performance and reduced power use. At the same time, concerns about data privacy during cloud-based model execution have led to the adoption of cryptographic methods. This article introduces BioEncryptSNN, a spiking neural network based encryption-decryption framework for secure and noise-resilient data protection. Unlike conventional algorithms, BioEncryptSNN converts ciphertext into spike trains and exploits temporal neural dynamics to model encryption and decryption, optimising parameters such as key length, spike timing, and synaptic connectivity. Benchmarked against AES-128, RSA-2048, and DES, BioEncryptSNN preserved data integrity while achieving up to 4.1x faster encryption and decryption than PyCryptodome's AES implementation. The framework demonstrates scalability and adaptability across symmetric and asymmetric ciphers, positioning SNNs as a promising direction for secure, energy-efficient computing.