Downloads · 30 days
0
Art_Ass_5_q2
kingkenche/Art_Ass_5_q2
Art_Ass_5_q2 is a machine learning model from kingkenche. 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 mit.
- ResNet-18 trained from scratch on CIFAR-10 (≥ 72% clean accuracy). - FGSM attack implemented from scratch and via IBM ART. - ResNet-34 binary detectors trained on PGD and BIM adversarial examples.
Access
Public
Updated Apr 3, 2026
Repo size
215 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth215 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026
- SHA
- 02f11e9c
Model card
From the Hugging Face model README
Assignment 5 – Adversarial Attacks & Detection (Q2)
Overview
- ResNet-18 trained from scratch on CIFAR-10 (≥ 72% clean accuracy).
- FGSM attack implemented from scratch and via IBM ART.
- ResNet-34 binary detectors trained on PGD and BIM adversarial examples.
Checkpoints
| File | Description |
|---|---|
checkpoints/resnet18_cifar10_best.pth | Best ResNet-18 classifier |
checkpoints/detector_pgd.pth | ResNet-34 PGD detector |
checkpoints/detector_bim.pth | ResNet-34 BIM detector |
Results
See results/ folder and the WandB project linked in the GitHub README.
- License
- mit
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026