Spiking Neural Networks (SNNs) are energy-efficient and biologically plausible, ideal for embedded and security-critical systems, yet their adversarial robustness remains open. Existing adversarial attacks often overlook SNNs' bio-plausible dynamics. We propose Spike-PTSD, a biologically inspired adversarial attack framework modeled on abnormal neural firing in Post-Traumatic Stress Disorder (PTSD). It localizes decision-critical layers, selects neurons via hyper/hypoactivation signatures, and optimizes adversarial examples with dual objectives. Across six datasets, three encoding types, and four models, Spike-PTSD achieves over 99% success rates, systematically compromising SNN robustness. Code: https://github.com/bluefier/Spike-PTSD.

翻译：脉冲神经网络（SNN）因其能效高且具有生物合理性，非常适合用于嵌入式系统和安全关键型应用，但其对抗鲁棒性仍是一个开放性问题。现有对抗攻击往往忽视了SNN的生物合理动态特性。我们提出Spike-PTSD，一种受创伤后应激障碍（PTSD）中异常神经放电启发而构建的生物合理性对抗攻击框架。该框架定位决策关键层，通过过度激活/欠激活特征选择神经元，并以双重目标优化对抗样本。在六个数据集、三种编码类型和四个模型上，Spike-PTSD实现了超过99%的攻击成功率，系统性地削弱了SNN的鲁棒性。代码：https://github.com/bluefier/Spike-PTSD。