Certified Robustness of Nearest Neighbors against Data Poisoning Attacks

Jinyuan Jia, Xiaoyu Cao, Neil Zhenqiang Gong

Abstract: Data poisoning attacks aim to corrupt a machine learning model via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted model predicts any or attacker-chosen incorrect labels for testing examples. The key idea of state-of-the-art certified defenses against data poisoning attacks is to create a \emph{majority vote} mechanism to predict the label of a testing example. Moreover, each voter is a base classifier trained on a subset of the training dataset. Nearest neighbor algorithms such as $k$ nearest neighbors (kNN) and radius nearest neighbors (rNN) have intrinsic majority vote mechanisms. In this work, we show that the intrinsic majority vote mechanisms in kNN and rNN already provide certified robustness guarantees against general data poisoning attacks. Moreover, our empirical evaluation results on MNIST and CIFAR10 show that the intrinsic certified robustness guarantees of kNN and rNN outperform those provided by state-of-the-art certified defenses.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2012.03765/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=P-q_sNzEvG