Combating Adversarial Attacks Using Sparse Representations

Authors: Soorya Gopalakrishnan, Zhinus Marzi, Upamanyu Madhow, Ramtin Pedarsani
Published: 2018-03-11 | Updated: 2018-07-13

Source: https://arxiv.org/abs/1803.03880

PDF: https://arxiv.org/pdf/1803.03880

Labels Predicted by AI

敵対的攻撃検出 バックドアモデルの検知 スパース表現

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

It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs). In this paper, we make the case that sparse representations of the input data are a crucial tool for combating such attacks. For linear classifiers, we show that a sparsifying front end is provably effective against ℓ_∞-bounded attacks, reducing output distortion due to the attack by a factor of roughly K/N where N is the data dimension and K is the sparsity level. We then extend this concept to DNNs, showing that a “locally linear” model can be used to develop a theoretical foundation for crafting attacks and defenses. Experimental results for the MNIST dataset show the efficacy of the proposed sparsifying front end.