Abstract
As Spiking Neural Networks (SNNs) gain traction across various applications, understanding their security vulnerabilities becomes increasingly important. In this work, we focus on the adversarial attacks, which is perhaps the most concerning threat. An adversarial attack aims at finding a subtle input perturbation to fool the network's decision-making. We propose two novel adversarial attack algorithms for SNNs: an input-specific attack that crafts adversarial samples from specific dataset inputs and a universal attack that generates a reusable patch capable of inducing misclassification across most inputs, thus offering practical feasibility for real-time deployment. The algorithms are gradient-based operating in the spiking domain proving to be effective across different evaluation metrics, such as adversarial accuracy, stealthiness, and generation time. Experimental results on two widely used neuromorphic vision datasets, NMNIST and IBM DVS Gesture, show that our proposed attacks surpass in all metrics all existing state-of-the-art methods. Additionally, we present the first demonstration of adversarial attack generation in the sound domain using the SHD dataset.
Abstract (translated)
随着尖峰神经网络（SNNs）在各种应用中的普及，了解其安全漏洞变得越来越重要。在这项工作中，我们重点关注对抗性攻击，这是最令人担忧的威胁之一。对抗性攻击旨在找到微小的输入扰动来误导网络的决策过程。我们提出了两种针对SNN的新颖对抗性攻击算法：一种是特定于输入的攻击，该攻击从特定数据集输入中创建对抗样本；另一种是通用攻击，它生成一个可重复使用的补丁，在大多数输入上都能引发分类错误，从而为实时部署提供实际可行性。这些算法基于梯度并在尖峰域内操作，证明在各种评估指标（如对抗准确性、隐蔽性和生成时间）下都非常有效。 我们在两个广泛使用的人工神经形态视觉数据集NMNIST和IBM DVS手势数据集上的实验结果显示，我们提出的攻击方法在所有指标上都超越了现有的最先进方法。此外，我们还首次展示了使用SHD数据集在声音域中生成对抗性攻击的方法。
URL
https://arxiv.org/abs/2505.06299
