Adversarial Training for Free!

Code

• github.com/mahyarnajibi/FreeAdversarialTraining
  OfficialIn paperpytorch★ 0
• github.com/ashafahi/free_adv_train
  OfficialIn papertf★ 0
• github.com/locuslab/fast_adversarial
  pytorch★ 445
• github.com/simon0987/Fast_FGSM
  pytorch★ 1
• github.com/AlanChou/Adversarial-Training-for-Free
  pytorch★ 0
• github.com/a1600012888/YOPO-You-Only-Propagate-Once
  pytorch★ 0

Abstract

Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks. Unfortunately, the high cost of generating strong adversarial examples makes standard adversarial training impractical on large-scale problems like ImageNet. We present an algorithm that eliminates the overhead cost of generating adversarial examples by recycling the gradient information computed when updating model parameters. Our "free" adversarial training algorithm achieves comparable robustness to PGD adversarial training on the CIFAR-10 and CIFAR-100 datasets at negligible additional cost compared to natural training, and can be 7 to 30 times faster than other strong adversarial training methods. Using a single workstation with 4 P100 GPUs and 2 days of runtime, we can train a robust model for the large-scale ImageNet classification task that maintains 40% accuracy against PGD attacks. The code is available at https://github.com/ashafahi/free_adv_train.

Tasks

Benchmark Results

Reproductions