Timezone: »

Adversarial training for free!
Ali Shafahi · Mahyar Najibi · Mohammad Amin Ghiasi · Zheng Xu · John Dickerson · Christoph Studer · Larry Davis · Gavin Taylor · Tom Goldstein

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #5

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.

Author Information

Ali Shafahi (University of Maryland)
Mahyar Najibi (University of Maryland)
Mohammad Amin Ghiasi (University of Maryland)
Zheng Xu (Google AI)
John Dickerson (University of Maryland)
Christoph Studer (Cornell University)
Larry Davis (University of Maryland)
Gavin Taylor (US Naval Academy)
Tom Goldstein (University of Maryland)

More from the Same Authors