Spike-PTSD: A Bio-Plausible Adversarial Example Attack on Spiking Neural Networks via PTSD-Inspired Spike Scaling

TL;DR

Spike-PTSD introduces a novel bio-inspired adversarial attack on spiking neural networks, exploiting PTSD-like neural firing patterns to systematically compromise their robustness across multiple datasets and models.

Contribution

It presents the first biologically inspired adversarial attack framework tailored for SNNs, enhancing understanding of their vulnerabilities.

Findings

Achieves over 99% attack success rate across various datasets and models.

Effectively localizes decision-critical layers in SNNs.

Demonstrates systematic vulnerability of SNNs to PTSD-inspired attacks.

Abstract

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.