Spike-PTSD: A Bio-Plausible Adversarial Example Attack on Spiking Neural Networks via PTSD-Inspired Spike Scaling
This addresses security vulnerabilities in SNNs for embedded and security-critical systems, representing a novel attack method rather than incremental improvement.
The paper tackles the problem of adversarial robustness in Spiking Neural Networks (SNNs) by proposing Spike-PTSD, a biologically inspired adversarial attack framework, and achieves over 99% success rates across multiple datasets and models.
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.