Research map / Image generation / Image restoration
Asynchronous Event Error-Minimizing Noise for Safeguarding Event Dataset
Ruofei Wang, Peiqi Duan, Boxin Shi, Renjie Wan
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 similarity loss to surrogate training (ablation) | UEvs sample-wise noise · N-Caltech101 (ResNet18) | test accuracy (%): 3.85 -> 0.52 | Improved |
| add similarity loss to surrogate training (ablation) | UEvs sample-wise noise · N-Caltech101 (ViT-B) | test accuracy (%): 37.51 -> 1.09 | Improved |
| mix class-wise and sample-wise noise by random selection (ablation) | UEvs sample-wise noise · N-Caltech101 (ResNet18) | test accuracy (%): 0.52 -> 5.17 | No clear effect |
| mix class-wise and sample-wise noise by addition (ablation) | UEvs sample-wise noise · N-Caltech101 (ResNet18) | test accuracy (%): 0.52 -> 5.34 | Mixed |
| hacker uses data augmentation (shift, crop, flip, event drop) (ablation) | UEvs sample-wise noise · N-Caltech101 (ResNet18) | test accuracy (%): 0.52 -> 13.04 | Hurt |
| generate noise with FGSM instead of PGD (ablation) | UEvs sample-wise noise · N-Caltech101 (ResNet18) | test accuracy (%): 0.52 -> 27.74 | Hurt |
| raise projection tau from 3/4 to 7/8 (ablation) | UEvs sample-wise noise · N-Caltech101 (ResNet18) | test accuracy (%): 0.52 -> 4.88 | Hurt |
| add noise projection to sparsify into {-0.5,0,0.5} (ablation) | UEvs sample-wise noise · event stream compatibility | reconstruction feasibility | Improved |
| use event frame representation instead of voxel stack (ablation) | class-wise noise · N-Caltech101 (ResNet50) | test accuracy (%): 5.17 | No clear effect |
| use time surface representation instead of voxel stack (ablation) | class-wise noise · N-Caltech101 (ResNet50) | test accuracy (%): 10.09 | No clear effect |
| use C&W instead of PGD for noise (ablation) | sample-wise noise · N-Caltech101 (ResNet50) | test accuracy (%): 12.15 | No clear effect |
| replace UEvs with event error-minimizing noise vs polarity inversion | UEvs sample-wise noise · N-Caltech101 (unlearnable test accuracy) | test accuracy (%): 40.78 -> 0.52 | Improved |
Closest papers by meaning
- Event Trojan: Asynchronous Event-based Backdoor Attacks (ECCV 2024 · similarity 0.86)
- Adversarial Attack for Asynchronous Event-Based Data (AAAI 2022 · similarity 0.83)
- Event-based Asynchronous Sparse Convolutional Networks (ECCV 2020 · similarity 0.82)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.81)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.81)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.80)
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.
