Securing deep spiking neural networks against adversarial attacks through inherent structural parameters
R El-Allami, A Marchisio, M Shafique… - … Design, Automation & …, 2021 - ieeexplore.ieee.org
Deep Learning (DL) algorithms have gained popularity owing to their practical problem-
solving capacity. However, they suffer from a serious integrity threat, ie, their vulnerability to …
solving capacity. However, they suffer from a serious integrity threat, ie, their vulnerability to …
Toward robust spiking neural network against adversarial perturbation
As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical
applications, the security concerns in SNNs attract more attention. Currently, researchers …
applications, the security concerns in SNNs attract more attention. Currently, researchers …
Inherent adversarial robustness of deep spiking neural networks: Effects of discrete input encoding and non-linear activations
In the recent quest for trustworthy neural networks, we present Spiking Neural Network
(SNN) as a potential candidate for inherent robustness against adversarial attacks. In this …
(SNN) as a potential candidate for inherent robustness against adversarial attacks. In this …
Is spiking secure? a comparative study on the security vulnerabilities of spiking and deep neural networks
A Marchisio, G Nanfa, F Khalid… - … Joint Conference on …, 2020 - ieeexplore.ieee.org
Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological
plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs) …
plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs) …
A comprehensive analysis on adversarial robustness of spiking neural networks
In this era of machine learning models, their functionality is being threatened by adversarial
attacks. In the face of this struggle for making artificial neural networks robust, finding a …
attacks. In the face of this struggle for making artificial neural networks robust, finding a …
Hire-snn: Harnessing the inherent robustness of energy-efficient deep spiking neural networks by training with crafted input noise
Low-latency deep spiking neural networks (SNNs) have become a promising alternative to
conventional artificial neural networks (ANNs) because of their potential for increased …
conventional artificial neural networks (ANNs) because of their potential for increased …
Snn-rat: Robustness-enhanced spiking neural network through regularized adversarial training
Spiking neural networks (SNNs) are promising to be widely deployed in real-time and safety-
critical applications with the advance of neuromorphic computing. Recent work has …
critical applications with the advance of neuromorphic computing. Recent work has …
Exploring adversarial attack in spiking neural networks with spike-compatible gradient
Spiking neural network (SNN) is broadly deployed in neuromorphic devices to emulate brain
function. In this context, SNN security becomes important while lacking in-depth …
function. In this context, SNN security becomes important while lacking in-depth …
Rate gradient approximation attack threats deep spiking neural networks
Abstract Spiking Neural Networks (SNNs) have attracted significant attention due to their
energy-efficient properties and potential application on neuromorphic hardware. State-of-the …
energy-efficient properties and potential application on neuromorphic hardware. State-of-the …
R-snn: An analysis and design methodology for robustifying spiking neural networks against adversarial attacks through noise filters for dynamic vision sensors
A Marchisio, G Pira, M Martina… - 2021 IEEE/RSJ …, 2021 - ieeexplore.ieee.org
Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities
when implemented on neuromorphic chips with event-based Dynamic Vision Sensors …
when implemented on neuromorphic chips with event-based Dynamic Vision Sensors …