Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations

by   Saima Sharmin, et al.

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 work, we demonstrate that accuracy degradation is less severe in SNNs than in their non-spiking counterparts for CIFAR10 and CIFAR100 datasets on deep VGG architectures. We attribute this robustness to two fundamental characteristics of SNNs and analyze their effects. First, we exhibit that input discretization introduced by the Poisson encoder improves adversarial robustness with reduced number of timesteps. Second, we quantify the amount of adversarial accuracy with increased leak rate in Leaky-Integrate-Fire (LIF) neurons. Our results suggest that SNNs trained with LIF neurons and smaller number of timesteps are more robust than the ones with IF (Integrate-Fire) neurons and larger number of timesteps. We overcome the bottleneck of creating gradient-based adversarial inputs in temporal domain by proposing a technique for crafting attacks from SNN.


page 1

page 2

page 3

page 4


HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds

Spiking neural networks (SNNs) offer promise for efficient and powerful ...

Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters

Deep Learning (DL) algorithms have gained popularity owing to their prac...

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks

In this era of machine learning models, their functionality is being thr...

Sharing Leaky-Integrate-and-Fire Neurons for Memory-Efficient Spiking Neural Networks

Spiking Neural Networks (SNNs) have gained increasing attention as energ...

A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networks

Research around Spiking Neural Networks has ignited during the last year...

Function Regression using Spiking DeepONet

One of the main broad applications of deep learning is function regressi...

Code Repositories



view repo

Please sign up or login with your details

Forgot password? Click here to reset