Fast Training of Provably Robust Neural Networks by SingleProp
Keywords:Adversarial Learning & Robustness
AbstractRecent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees. However, these techniques can be computationally costly due to the use of certification during training. We develop a new regularizer that is both more efficient than existing certified defenses, requiring only one additional forward propagation through a network, and can be used to train networks with similar certified accuracy. Through experiments on MNIST and CIFAR-10 we demonstrate improvements in training speed and comparable certified accuracy compared to state-of-the-art certified defenses.
How to Cite
Boopathy, A., Weng, L., Liu, S., Chen, P.-Y., Zhang, G., & Daniel, L. (2021). Fast Training of Provably Robust Neural Networks by SingleProp. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 6803-6811. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16840
AAAI Technical Track on Machine Learning I