Physics

Meteorology

Gene

Operating system

Computer engineering

Machine learning

Engineering

Artificial intelligence

Systems engineering

Chemistry

Training (meteorology)

Scale (ratio)

Overhead (engineering)

Computer science

Task (project management)

Quantum mechanics

Adversarial system

Biochemistry

Robustness (evolution)

Workstation

arXiv (Cornell University)

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.

Adversarial training for free