Adversarial Risk Bounds via Function Transformation
We derive bounds for a notion of adversarial risk, designed to characterize the robustness of linear and neural network classifiers to adversarial perturbations. Specifically, we introduce a new class of function transformations with the property that the risk of the transformed functions upper-bounds the adversarial risk of the original functions. This reduces the problem of deriving bounds on the adversarial risk to the problem of deriving risk bounds using standard learning-theoretic techniques. We then derive bounds on the Rademacher complexities of the transformed function classes, obtaining error rates on the same order as the generalization error of the original function classes. We also discuss extensions of our theory to multiclass classification and regression. Finally, we provide two algorithms for optimizing the adversarial risk bounds in the linear case, and discuss connections to regularization and distributional robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Lossless Transformations and Excess Risk Bounds in Statistical Inference
We study the excess minimum risk in statistical inference, defined as the difference between the minimum expected loss in estimating a random variable from an observed feature vector and the minimum expected loss in esti…
Adversarial Surrogate Risk Bounds for Binary Classification
A central concern in classification is the vulnerability of machine learning models to adversarial attacks. Adversarial training is one of the most popular techniques for training robust classifiers, which involves minim…
Binary ClassificationClassificationLower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions
We consider adversarially robust classification in a multiclass setting under arbitrary loss functions and derive dual and barycentric reformulations of the corresponding learner-agnostic robust risk minimization problem…
Adversarial RobustnessNon-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models
We propose a general approach to evaluating the performance of robust estimators based on adversarial losses under misspecified models. We first show that adversarial risk is equivalent to the risk induced by a distribut…
Adversarial AttackregressionTheoretical Analysis of Adversarial Learning: A Minimax Approach
Here we propose a general theoretical method for analyzing the risk bound in the presence of adversaries. Specifically, we try to fit the adversarial learning problem into the minimax framework. We first show that the or…
Adversarial RobustnessGeneral ClassificationMulti-class Classification