Research map / Adversarial robustness and security / Certified and empirical robustness
Robust Spiking Neural Networks Against Adversarial Attacks
Shuai Wang, Malu Zhang, Yulin Jiang, Dehao Zhang, Ammar Belatreche, Yu Liang, Yimeng Shan, Zijian Zhou, Yang Yang, Haizhou Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add membrane potential constraint (ablation) | vanilla BPTT SNN · CIFAR-100 (VGG-11) | FGSM accuracy: 5.9 -> 17.1 | Improved |
| add noisy-LIF neurons (ablation) | vanilla BPTT SNN · CIFAR-100 (VGG-11) | FGSM accuracy: 5.9 -> 8.1 | Improved |
| add noisy-LIF to membrane constraint (ablation) | BPTT SNN with MC · CIFAR-100 (VGG-11) | FGSM accuracy: 17.1 -> 21.5 | Improved |
| add membrane constraint (ablation) | vanilla BPTT SNN · CIFAR-100 (VGG-11) | clean accuracy: 71.4 -> 64.3 | Hurt |
| add membrane constraint (ablation) | RAT SNN · CIFAR-100 (VGG-11) | RFGSM accuracy: 46.2 -> 42.7 | Hurt |
| add membrane constraint (ablation) | RAT SNN · CIFAR-100 (VGG-11) | FGSM accuracy: 20.9 -> 26.2 | Improved |
| add noisy-LIF neurons (ablation) | RAT SNN · CIFAR-100 (VGG-11) | PGD40 accuracy: 6.9 -> 9.1 | Improved |
| add TGO to vanilla BPTT | WRN-16 · CIFAR-10 | FGSM accuracy: 14.05 -> 51.40 | Improved |
| add TGO to vanilla BPTT | WRN-16 · CIFAR-10 | clean accuracy: 93.32 -> 88.79 | Hurt |
| add TGO to RAT | WRN-16 · CIFAR-10 | PGD40 accuracy: 14.18 -> 33.13 | Improved |
| replace SR with TGO on AT | WRN-16 AT · CIFAR-100 (MTPGD7, EoT) | accuracy: 16.88 -> 21.23 | Improved |
| replace SR with TGO on AT | WRN-16 AT · CIFAR-100 (APGD7, EoT) | accuracy: 14.48 -> 18.93 | Improved |
Closest papers by meaning
- Robust Stable Spiking Neural Networks (ICML 2024 · similarity 0.91)
- Enhancing Adversarial Robustness in SNNs with Sparse Gradients (ICML 2024 · similarity 0.90)
- Enhancing the Robustness of Spiking Neural Networks with Stochastic Gating Mechanisms (AAAI 2024 · similarity 0.90)
- FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor (NeurIPS 2024 · similarity 0.89)
- Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients (CVPR 2025 · similarity 0.89)
- 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.
