Downloads · 30 days
0
pixel-shield
ARotting/pixel-shield
pixel-shield is a machine learning model from ARotting. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
PixelShield stress-tests the 2,198-parameter Tiny Vision student against Fast Gradient Sign Method perturbations, then adversarially fine-tunes an architecture-identical copy.
Access
Public
Updated Jul 30, 2026
Parameters
2.2K
9.4 KB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.4 KB · 47%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- a4d55b62
Model card
From the Hugging Face model README
PixelShield
PixelShield stress-tests the 2,198-parameter Tiny Vision student against Fast Gradient Sign Method perturbations, then adversarially fine-tunes an architecture-identical copy.
The benchmark reports clean accuracy and robust accuracy at several normalized pixel-space perturbation budgets. FGSM is a first-order white-box attack, so this project is an educational robustness baseline rather than a security guarantee.
Reproduce
uv run python projects/tiny-vision-foundry/prepare_data.py
uv run python projects/pixel-shield/train.py
Verified results
| FGSM epsilon | Baseline accuracy | Adversarially trained | Change |
|---|---|---|---|
| 0.00 | 98.52% | 94.44% | -4.07 points |
| 0.05 | 82.96% | 89.26% | +6.30 points |
| 0.10 | 46.30% | 74.81% | +28.52 points |
| 0.15 | 20.37% | 55.56% | +35.19 points |
| 0.20 | 12.22% | 32.59% | +20.37 points |
| 0.25 | 7.04% | 14.07% | +7.04 points |
The robust model has the same 2,198 parameters as the baseline. Its clean-accuracy cost is 4.07 percentage points. Results use a white-box FGSM attack against each model separately, avoiding transfer-attack inflation.
- License
- apache-2.0
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026