Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples

Authors: Hajime Ono, Tsubasa Takahashi, Kazuya Kakizaki
Published: 2018-11-20

Source: https://arxiv.org/abs/1811.08080

PDF: https://arxiv.org/pdf/1811.08080

Labels Predicted by AI

ロバスト性向上 敵対的学習 防御手法

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure ϵ-robust, consume huge resources, they can only achieve small degree of robustness in practice. Lipschitz margin training (LMT) is a scalable certified defense, but it can also only achieve small robustness due to over-regularization. How can we make certified defense more efficiently? We present LC-LMT, a light weight Lipschitz margin training which solves the above problem. Our method has the following properties; (a) efficient: it can achieve ϵ-robustness at early epoch, and (b) robust: it has a potential to get higher robustness than LMT. In the evaluation, we demonstrate the benefits of the proposed method. LC-LMT can achieve required robustness more than 30 epoch earlier than LMT in MNIST, and shows more than 90 % accuracy against both legitimate and adversarial inputs.