Defending Against Adversarial Examples with K-Nearest Neighbor
Abstract
Robustness is an increasingly important property of machine learning models as they become more and more prevalent. We propose a defense against adversarial examples based on a k-nearest neighbor (kNN) on the intermediate activation of neural networks. Our scheme surpasses state-of-the-art defenses on MNIST and CIFAR-10 against l2-perturbation by a significant margin. With our models, the mean perturbation norm required to fool our MNIST model is 3.07 and 2.30 on CIFAR-10. Additionally, we propose a simple certifiable lower bound on the l2-norm of the adversarial perturbation using a more specific version of our scheme, a 1-NN on representations learned by a Lipschitz network. Our model provides a nontrivial average lower bound of the perturbation norm, comparable to other schemes on MNIST with similar clean accuracy.
Keywords
Cite
@article{arxiv.1906.09525,
title = {Defending Against Adversarial Examples with K-Nearest Neighbor},
author = {Chawin Sitawarin and David Wagner},
journal= {arXiv preprint arXiv:1906.09525},
year = {2020}
}
Comments
Inadequate experimental evaluation