Print Email Facebook Twitter Revealing the Secrets of Spiking Neural Networks Title Revealing the Secrets of Spiking Neural Networks: The Case of Izhikevich Neuron Author Caetano Garaffa, L. (TU Delft Computer Engineering) Aljuffri, A.A.M. (TU Delft Computer Engineering) Reinbrecht, Cezar (TU Delft Computer Engineering) Hamdioui, S. (TU Delft Quantum & Computer Engineering) Taouil, M. (TU Delft Computer Engineering) Sepulveda, Johanna (AirBus Defence and Space GmbH) Contributor O'Conner, L. (editor) Department Quantum & Computer Engineering Date 2021 Abstract 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. To reference this document use: http://resolver.tudelft.nl/uuid:e362f053-3d90-4466-ba45-e62021f68fb8 DOI https://doi.org/10.1109/DSD53832.2021.00083 Publisher IEEE, Piscataway ISBN 978-1-6654-2704-3 Source 2021 24th Euromicro Conference on Digital System Design (DSD): Proceedings Event 2021 24th Euromicro Conference on Digital System Design (DSD), 2021-09-01 → 2021-09-03, Virtual at Palermo, Spain Bibliographical note Accepted author manuscript Part of collection Institutional Repository Document type conference paper Rights © 2021 L. Caetano Garaffa, A.A.M. Aljuffri, Cezar Reinbrecht, S. Hamdioui, M. Taouil, Johanna Sepulveda Files PDF DSD_NEURO_FINAL_SHORTPAPE ... AX5_3_.pdf 580.28 KB Close viewer /islandora/object/uuid:e362f053-3d90-4466-ba45-e62021f68fb8/datastream/OBJ/view