MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization

Runhao Jiang; Chengzhi Jiang; Rui Yan; Huajin Tang

AAAI 2026technical0 citations

MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization

Runhao Jiang, Chengzhi Jiang, Rui Yan, Huajin Tang

Abstract

The surrogate gradient (SG) method has shown significant promise in enhancing the performance of deep spiking neural networks (SNNs), but it also introduces vulnerabilities to adversarial attacks. Although spike coding strategies and neural dynamics parameters have been extensively studied for their impact on robustness, the critical role of gradient magnitude, which reflects the model

BibTeX

@inproceedings{aaai2026_mpdsgrrobustspik,
  title = {MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization},
  author = {Runhao Jiang and Chengzhi Jiang and Rui Yan and Huajin Tang},
  booktitle = {AAAI 2026},
  year = {2026}
}