Revealing the Secrets of Spiking Neural Networks: The Case of Izhikevich Neuron

Autor:	Caetano Garaffa, L., Aljuffri, A.A.M., Reinbrecht, Cezar, Hamdioui, S., Taouil, M., Sepulveda, Johanna, O'Conner, L.
Rok vydání:	2021
Předmět:	Reverse engineering Spiking neural network Artificial neural network business.industry Computer science Deep learning Cyber-physical system Biological neuron model computer.software_genre Field (computer science) Information leakage Artificial intelligence business computer
Zdroj:	DSD 2021 24th Euromicro Conference on Digital System Design (DSD): Proceedings 2021 24th Euromicro Conference on Digital System Design (DSD)
DOI:	10.1109/dsd53832.2021.00083
Popis:	Spiking Neural Networks (SNNs) are a strong candidate to be used in future machine learning applications. SNNs can obtain the same accuracy of complex deep learning networks, while only using a fraction of its power. As a result, an increase in popularity of SNNs is expected in the near future for cyber physical systems, especially in the Internet of Things (IoT) segment. However, SNNs work very different than conventional neural network architectures. Consequently, applying SNNs in the field might introduce new unexpected security vulnerabilities. This paper explores and identifies potential sources of information leakage for the Izhikevich neuron, which is a popular neuron model used in digital implementations of SNNs. Simulations and experiments on FPGA implementation of the spiking neurons show that timing and power can be used to infer important information of the internal functionality of the network. Additionally, the paper demonstrates that is feasible to perform a reverse engineering attack using both power and timing leakage.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f5f5357a8883940b1c7e7db19d942fc https://doi.org/10.1109/dsd53832.2021.00083 Zobrazit plný text záznamu