https://github.com/igitugraz/robustsnnconversion

Code for "Adversarially Robust Spiking Neural Networks Through Conversion" [TMLR 2024]
https://github.com/igitugraz/robustsnnconversion

adversarial-attacks adversarial-robustness ann-to-snn-conversion snn spiking-neural-networks

Last synced: 22 days ago
JSON representation

Code for "Adversarially Robust Spiking Neural Networks Through Conversion" [TMLR 2024]

• Host: GitHub
• URL: https://github.com/igitugraz/robustsnnconversion
• Owner: IGITUGraz
• License: mit
• Created: 2023-11-15T08:35:54.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-12T09:15:28.000Z (9 months ago)
• Last Synced: 2024-11-08T03:38:16.177Z (2 months ago)
• Topics: adversarial-attacks, adversarial-robustness, ann-to-snn-conversion, snn, spiking-neural-networks
• Language: Python
• Homepage:
• Size: 29.3 KB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Adversarially Robust Spiking Neural Networks Through Conversion

This is the code repository of the following [paper](https://openreview.net/pdf?id=I8FMYa2BdP) to perform adversarially robust ANN-to-SNN conversion.

"Adversarially Robust Spiking Neural Networks Through Conversion"\

Ozan Özdenizci, Robert Legenstein\

Transactions on Machine Learning Research (TMLR), 2024.\

https://openreview.net/forum?id=I8FMYa2BdP

## Reference

If you use this code or models in your research and find it helpful, please cite the following paper:

```

@article{ozdenizci2024adversarially,

  title={Adversarially robust spiking neural networks through conversion},

  author={Ozan {\"O}zdenizci and Robert Legenstein},

  journal={Transactions on Machine Learning Research},

  year={2024}

}

```

## Acknowledgments

Authors of this work are affiliated with Graz University of Technology, Institute of Theoretical Computer Science, and Silicon Austria Labs, TU Graz - SAL Dependable Embedded Systems Lab, Graz, Austria. This work has been supported by the "University SAL Labs" initiative of Silicon Austria Labs (SAL) and its Austrian partner universities for applied fundamental research for electronic based systems.

Parts of this code repository is based on the following works:

* https://github.com/nitin-rathi/hybrid-snn-conversion

* https://github.com/putshua/SNN-RAT