Add Adversarial Training with Early Stopping (ATES), CIFAR-100 · Issue #22 · fra31/auto-attack (original) (raw)

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.