Robustness for Non-Parametric Classification: A Generic Attack and Defense
Adversarially robust machine learning has received much recent attention. However, prior attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or classifier-specific basis. In this work, we take a holistic look at adversarial examples for non-parametric classifiers, including nearest neighbors, decision trees, and random forests. We provide a general defense method, adversarial pruning, that works by preprocessing the dataset to become well-separated. To test our defense, we provide a novel attack that applies to a wide range of non-parametric classifiers. Theoretically, we derive an optimally robust classifier, which is analogous to the Bayes Optimal. We show that adversarial pruning can be viewed as a finite sample approximation to this optimal classifier. We empirically show that our defense and attack are either better than or competitive with prior work on non-parametric classifiers. Overall, our results provide a strong and broadly-applicable baseline for future work on robust non-parametrics. Code available at https://github.com/yangarbiter/adversarial-nonparametrics/ .
Code (1)
Tasks
Adversarial AttackAdversarial DefenseClassificationGeneral ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On The Adversarial Robustness of 3D Point Cloud Classification
3D point clouds play pivotal roles in various safety-critical fields, such as autonomous driving, which desires the corresponding deep neural networks to be robust to adversarial perturbations. Though a few defenses agai…
3D Point Cloud ClassificationAdversarial RobustnessAutonomous DrivingClassification+1On Adversarial Robustness of 3D Point Cloud Classification under Adaptive Attacks
3D point clouds play pivotal roles in various safety-critical applications, such as autonomous driving, which desires the underlying deep neural networks to be robust to adversarial perturbations. Though a few defenses a…
3D Point Cloud ClassificationAdversarial RobustnessAutonomous DrivingGeneral Classification+1PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks
Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to gen…
Visual Question AnsweringCertified Robustness to Adversarial Examples with Differential Privacy
Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past de…
Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoot…
Image Classification