Skip to content
Back to skills

Adversarially Robust Spiking Neural Networks Through Conversion

ASecurity

**arXiv ID:** 2311.09266 **Authors:** Ozan Özdenizci, Robert Legenstein **Published:** 2023-11-15T08:33:46Z **Abstract:** Spiking neural networks (SNNs) provide an energy-efficient alternative to a variety of artificial neural network (ANN) based AI applications. As the progress in neuromorphic computing with SNNs expands their use in applications, the problem of adversarial robustness of SNNs becomes more pronounced. To the contrary of the widely explored end-to-end adversarial training base...

  • 3 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 11, 2026
toolsgo

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill adversarially-robust-spiking-neural-networks-through-conversion --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adversarially Robust Spiking Neural Networks Through Conversion?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Adversarially Robust Spiking Neural Networks Through Conversion
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-adversarially-robust-spiking-neural-networks-throu/badge)](https://www.skillsdirectory.com/skills/hiyenwong-adversarially-robust-spiking-neural-networks-throu)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Adversarially Robust Spiking Neural Networks Through Conversion

**arXiv ID:** 2311.09266
**Authors:** Ozan Özdenizci, Robert Legenstein
**Published:** 2023-11-15T08:33:46Z
**Abstract:**
Spiking neural networks (SNNs) provide an energy-efficient alternative to a variety of artificial neural network (ANN) based AI applications. As the progress in neuromorphic computing with SNNs expands their use in applications, the problem of adversarial robustness of SNNs becomes more pronounced. To the contrary of the widely explored end-to-end adversarial training based solutions, we address the limited progress in scalable robust SNN training methods by proposing an adversarially robust ANN-to-SNN conversion algorithm. Our method provides an efficient approach to embrace various computationally demanding robust learning objectives that have been proposed for ANNs. During a post-conversion robust finetuning phase, our method adversarially optimizes both layer-wise firing thresholds and synaptic connectivity weights of the SNN to maintain transferred robustness gains from the pre-trained ANN. We perform experimental evaluations in a novel setting proposed to rigorously assess the robustness of SNNs, where numerous adaptive adversarial attacks that account for the spike-based operation dynamics are considered. Results show that our approach yields a scalable state-of-the-art solution for adversarially robust deep SNNs with low-latency.

## Skill Description

This skill is generated from the arXiv paper: Adversarially Robust Spiking Neural Networks Through Conversion (2311.09266).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2311.09266](http://arxiv.org/abs/2311.09266v2)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.