Lower 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. We provide explicit characterizations for important cases such as the cross-entropy loss, loss functions with a power form, and the quadratic loss, extending in this way available results for the 0-1 loss. These reformulations enable efficient computation of sharp lower bounds for adversarial risks and facilitate the design of robust classifiers beyond the 0-1 loss setting. Our paper uncovers interesting connections between adversarial robustness, $α$-fair packing problems, and generalized barycenter problems for arbitrary positive measures where Kullback-Leibler and Tsallis entropies are used as penalties. Our theoretical results are accompanied with illustrative numerical experiments where we obtain tighter lower bounds for adversarial risks with the cross-entropy loss function.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification
Despite the success of deep learning-based algorithms, it is widely known that neural networks may fail to be robust. A popular paradigm to enforce robustness is adversarial training (AT), however, this introduces many c…
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 transfo…
General ClassificationUnveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory
Randomization as a mean to improve the adversarial robustness of machine learning models has recently attracted significant attention. Unfortunately, much of the theoretical analysis so far has focused on binary classifi…
Adversarial RobustnessBinary ClassificationClassificationCharacterization of Overfitting in Robust Multiclass Classification
This paper considers the following question: Given the number of classes m, the number of robust accuracy queries k, and the number of test examples in the dataset n, how much can adaptive algorithms robustly overfit the…
Sparse Representations Improve Adversarial Robustness of Neural Network Classifiers
Deep neural networks perform remarkably well on image classification tasks but remain vulnerable to carefully crafted adversarial perturbations. This work revisits linear dimensionality reduction as a simple, data-adapte…
Dimensionality ReductionAdversarial RobustnessImage Classification