Add Adversarial Training with Early Stopping (ATES), CIFAR-100 #22
Description
Paper: Improving Adversarial Robustness Through Progressive Hardening https://arxiv.org/abs/2003.09347
Venue: under review
Dataset and threat model: CIFAR-100, L-inf, 8/255
Code: https://github.com/chawins/ates-minimal
Pre-trained model: weight
Log file: log
Additional data: no
Clean and robust accuracy: 62.82/24.57
Architecture: WRN-34-10
Description of the model/defense: We use the curriculum learning framework to schedule the "difficulty" of adversarial examples generated during adversarial training. This improves both clean and robust accuracy.