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

2020-03-23 · ECCV 2020 8 · Saima Sharmin, Nitin Rathi, Priyadarshini Panda, Kaushik Roy

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 adversarial accuracy of SNNs under gradient-based attacks is higher than their non-spiking counterparts for CIFAR datasets on deep VGG and ResNet architectures, particularly in blackbox attack scenario. 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. Also we overcome the bottleneck of creating gradient-based adversarial inputs in temporal domain by proposing a technique for crafting attacks from SNN

📄 PDF Abstract BibTeX arXiv:2003.10399

Code (1)

ssharmin/spikingNN-adversarial-attack 공식 구현 pytorch

Tasks

Adversarial RobustnessAttribute

Methods 이 논문이 사용한 방법론

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Average Pooling 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Residual Connection 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Kaiming Initialization 설명 없음

Batch Normalization 설명 없음

Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

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

2020-12-09 · Rida El-Allami, Alberto Marchisio, Muhammad Shafique, Ihsen Alouani

Deep Learning (DL) algorithms have gained popularity owing to their practical problem-solving capacity. However, they suffer from a serious integrity threat, i.e., their vulnerability to adversarial attacks. In the quest…

RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding

2024-07-29 · Keming Wu, Man Yao, Yuhong Chou, Xuerui Qiu 외

Spiking Neural Networks (SNNs) have received widespread attention due to their unique neuronal dynamics and low-power nature. Previous research empirically shows that SNNs with Poisson coding are more robust than Artific…

Adversarial Robustness

Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail

2025-09-28 · Luu Trong Nhan, Luu Trung Duong, Pham Ngoc Nam, Truong Cong Thang arxiv

Spiking Neural Networks (SNNs) have attracted growing interest in both computational neuroscience and artificial intelligence, primarily due to their inherent energy efficiency and compact memory footprint. However, achi…

Adversarial Robustness Adversarial Defense

Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble

2025-08-15 · Jihang Wang, Dongcheng Zhao, Ruolin Chen, Qian Zhang 외 arxiv

Spiking Neural Networks (SNNs) offer a promising direction for energy-efficient and brain-inspired computing, yet their vulnerability to adversarial perturbations remains poorly understood. In this work, we revisit the a…