Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs). Recent works have shown that DNNs are vulnerable to adversarial attacks, i.e., small perturbations added to the input data can lead to targeted or random misclassifications. In this paper, we aim at investigating the key research question: "Are SNNs secure?" Towards this, we perform a comparative study of the security vulnerabilities in SNNs and DNNs w.r.t. the adversarial noise. Afterwards, we propose a novel black-box attack methodology, i.e., without the knowledge of the internal structure of the SNN, which employs a greedy heuristic to automatically generate imperceptible and robust adversarial examples (i.e., attack images) for the given SNN. We perform an in-depth evaluation for a Spiking Deep Belief Network (SDBN) and a DNN having the same number of layers and neurons (to obtain a fair comparison), in order to study the efficiency of our methodology and to understand the differences between SNNs and DNNs w.r.t. the adversarial examples. Our work opens new avenues of research towards the robustness of the SNNs, considering their similarities to the human brain's functionality.
Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks / Marchisio, Alberto; Nanfa, Giorgio; Khalid, Faiq; Hanif, Muhammad Abdullah; Martina, Maurizio; Shafique, Muhammad. - ELETTRONICO. - 1:(2020), pp. 1-8. (Intervento presentato al convegno 2020 International Joint Conference on Neural Networks (IJCNN) tenutosi a Glasgow (UK) nel 19-24 July 2020) [10.1109/IJCNN48605.2020.9207297].
Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks
Martina, Maurizio;
2020
Abstract
Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs). Recent works have shown that DNNs are vulnerable to adversarial attacks, i.e., small perturbations added to the input data can lead to targeted or random misclassifications. In this paper, we aim at investigating the key research question: "Are SNNs secure?" Towards this, we perform a comparative study of the security vulnerabilities in SNNs and DNNs w.r.t. the adversarial noise. Afterwards, we propose a novel black-box attack methodology, i.e., without the knowledge of the internal structure of the SNN, which employs a greedy heuristic to automatically generate imperceptible and robust adversarial examples (i.e., attack images) for the given SNN. We perform an in-depth evaluation for a Spiking Deep Belief Network (SDBN) and a DNN having the same number of layers and neurons (to obtain a fair comparison), in order to study the efficiency of our methodology and to understand the differences between SNNs and DNNs w.r.t. the adversarial examples. Our work opens new avenues of research towards the robustness of the SNNs, considering their similarities to the human brain's functionality.File | Dimensione | Formato | |
---|---|---|---|
09207297.pdf
accesso riservato
Descrizione: Versione editoriale
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.51 MB
Formato
Adobe PDF
|
1.51 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
nanfa_IJCNN.pdf
accesso aperto
Descrizione: Versione autore
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
1.01 MB
Formato
Adobe PDF
|
1.01 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2847482