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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
2.2k params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support