Research map / Architectures and efficiency / Spiking networks
Do Not Let Spikes Flip: Margin-Resculpted Learning for Robust Spiking Neural Networks
Desong Zhang, Jia Hu, Geyong Min
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a margin-resculpting learning approach to improve adversarial robustness of spiking neural networks by analyzing robustness through the stability of spike decisions.
Problem
Adversarial robustness of spiking neural networks, where existing methods inherit ANN-oriented objectives that suppress continuous perturbations or stabilize membrane-potential dynamics rather than addressing discrete spike flips.
Approach
Argues SNN robustness should be analyzed through the stability of discrete spike decisions (spikes flipping under perturbation), and resculpts decision margins accordingly, instead of ANN-style smoothness or membrane-potential stabilization objectives.
Closest papers by meaning
- Robust Stable Spiking Neural Networks (ICML 2024 · similarity 0.92)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.90)
- Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients (NeurIPS 2026 · similarity 0.90)
- Enhancing the Robustness of Spiking Neural Networks with Stochastic Gating Mechanisms (AAAI 2024 · similarity 0.89)
- FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor (NeurIPS 2024 · similarity 0.88)
- S$^2$NN: Sub-bit Spiking Neural Networks (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
