Unique properties of adversarially trained linear classifiers on Gaussian data
Machine learning models are vulnerable to adversarial perturbations, that when added to an input, can cause high confidence misclassifications. The adversarial learning research community has made remarkable progress in the understanding of the root causes of adversarial perturbations. However, most problems that one may consider important to solve for the deployment of machine learning in safety critical tasks involve high dimensional complex manifolds that are difficult to characterize and study. It is common to develop adversarially robust learning theory on simple problems, in the hope that insights will transfer to `real world datasets'. In this work, we discuss a setting where this approach fails. In particular, we show with a linear classifier, it is always possible to solve a binary classification problem on Gaussian data under arbitrary levels of adversarial corruption during training, and that this property is not observed with non-linear classifiers on the CIFAR-10 dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningBinary ClassificationLearning TheorySimilar Papers 제목 키워드 기반
Benign Overfitting in Adversarially Robust Linear Classification
"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon…
ClassificationAdversarial Quantum Machine Learning: An Information-Theoretic Generalization Analysis
In a manner analogous to their classical counterparts, quantum classifiers are vulnerable to adversarial attacks that perturb their inputs. A promising countermeasure is to train the quantum classifier by adopting an att…
Quantum Machine LearningIntriguing Properties of Adversarial Examples
It is becoming increasingly clear that many machine learning classifiers are vulnerable to adversarial examples. In attempting to explain the origin of adversarial examples, previous studies have typically focused on the…
Adversarial RobustnessNeural Architecture SearchReinforcement LearningProvably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, …
Adversarial AttackAdversarial DefenseDeep LearningOn the Adversarial Robustness of Causal Algorithmic Recourse
Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems. Recourse recommendations should ideally be robust t…
Adversarial RobustnessDecision Making