While spiking neural networks (SNNs) offer a promising neurally-inspired model of computation, they are vulnerable to adversarial attacks. We present the first study that draws inspiration from neural homeostasis to design a threshold-adapting leaky integrate-and-fire (TA-LIF) neuron model and utilize TA-LIF neurons to construct the adversarially robust homeostatic SNNs (HoSNNs) for improved robustness. The TA-LIF model incorporates a self-stabilizing dynamic thresholding mechanism, offering a local feedback control solution to the minimization of each neuron's membrane potential error caused by adversarial disturbance. Theoretical analysis demonstrates favorable dynamic properties of TA-LIF neurons in terms of the bounded-input bounded-output stability and suppressed time growth of membrane potential error, underscoring their superior robustness compared with the standard LIF neurons. When trained with weak FGSM attacks (attack budget = 2/255) and tested with much stronger PGD attacks (attack budget = 8/255), our HoSNNs significantly improve model accuracy on several datasets: from 30.54% to 74.91% on FashionMNIST, from 0.44% to 35.06% on SVHN, from 0.56% to 42.63% on CIFAR10, from 0.04% to 16.66% on CIFAR100, over the conventional LIF-based SNNs.

翻译：尽管脉冲神经网络（SNNs）作为一种具有前景的神经启发计算模型，但其易受对抗攻击。本研究首次从神经稳态现象中汲取灵感，设计了一种阈值自适应漏积分发放（TA-LIF）神经元模型，并利用TA-LIF神经元构建了对抗鲁棒的稳态脉冲神经网络（HoSNNs）以提升其鲁棒性。TA-LIF模型引入了一种自稳定的动态阈值调节机制，为最小化由对抗扰动引起的每个神经元膜电位误差提供了一种局部反馈控制解决方案。理论分析表明，TA-LIF神经元在输入有界输出有界稳定性以及膜电位误差随时间增长受抑制方面具有良好的动态特性，这凸显了其相较于标准LIF神经元的卓越鲁棒性。当使用弱FGSM攻击（攻击预算 = 2/255）进行训练，并使用更强的PGD攻击（攻击预算 = 8/255）进行测试时，我们的HoSNNs在多个数据集上显著提升了模型准确率：在FashionMNIST上从30.54%提升至74.91%，在SVHN上从0.44%提升至35.06%，在CIFAR10上从0.56%提升至42.63%，在CIFAR100上从0.04%提升至16.66%，均优于传统的基于LIF的SNNs。