← Back ◬ AI & Machine Learning Apr 03, 2026

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

arXiv Security Archived Apr 03, 2026 ✓ Full text saved

arXiv:2604.01750v1 Announce Type: new 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 ne

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Cryptography and Security [Submitted on 2 Apr 2026] Spike-PTSD: A Bio-Plausible Adversarial Example Attack on Spiking Neural Networks via PTSD-Inspired Spike Scaling Lingxin Jin, Wei Jiang, Maregu Assefa Habtie, Letian Chen, Jinyu Zhan, Xingzhi Zhou, Lin Zuo, Naoufel Werghi 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: this https URL. Comments: This work was accepted by DAC 2026 Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2604.01750 [cs.CR] (or arXiv:2604.01750v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2604.01750 Focus to learn more Submission history From: Lingxin Jin [view email] [v1] Thu, 2 Apr 2026 08:10:35 UTC (5,677 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev | next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes