Research map / Adversarial robustness and security / Attacks on text and graphs
Exploring Vulnerabilities in Spiking Neural Networks: Direct Adversarial Attacks on Raw Event Data
Yanmeng Yao, Xiaohan Zhao, Bin Gu
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 |
|---|---|---|---|
| replace FGSM with Gumbel-Softmax plus straight-through optimization and position selection | raw event attack on SEW ResNet-34 · CIFAR10-DVS | ASR: 19.70% -> 72.23% | Improved |
| replace FGSM with the proposed attack on DVS gesture | raw event attack on SEW ResNet-34 · DVS gesture | ASR: 15.56% -> 86.67% | Improved |
| replace FGSM with the proposed attack on events changed | raw event attack · CIFAR10-DVS, SEW ResNet-34 | event change ratio: 34% -> 15% | Improved |
| use proposed attack on binary grid representation instead of Spike-Compatible | binary grid attack · CIFAR10-DVS, SEW ResNet-34 | ASR: 96.98% -> 95.45% | No clear effect |
| use proposed attack on binary grid vs Spike-Compatible on N-MNIST Spiking ResNet-18 | binary grid attack · N-MNIST, Spiking ResNet-18 | ASR: 94.86% -> 86.87% | Hurt |
| use proposed attack instead of SpikeFool on binary grid | binary grid attack · CIFAR10-DVS, SEW ResNet-34 | ASR: 29.60% -> 95.45% | Improved |
| use hard values with straight-through estimator instead of soft continuous values (ablation) | raw event attack · DVS gesture, SEW ResNet-34 | ASR: 100.00% -> 86.67% | Hurt |
Closest papers by meaning
- Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients (CVPR 2025 · similarity 0.91)
- Enhancing Adversarial Robustness in SNNs with Sparse Gradients (ICML 2024 · similarity 0.87)
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.87)
- SFOD: Spiking Fusion Object Detector (CVPR 2024 · similarity 0.87)
- Spiking Neural Network as Adaptive Event Stream Slicer (NeurIPS 2024 · similarity 0.86)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.86)
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.
