Cost-Sensitive Robustness against Adversarial Examples
Several recent works have developed methods for training classifiers that are certifiably robust against norm-bounded adversarial perturbations. These methods assume that all the adversarial transformations are equally important, which is seldom the case in real-world applications. We advocate for cost-sensitive robustness as the criteria for measuring the classifier's performance for tasks where some adversarial transformation are more important than others. We encode the potential harm of each adversarial transformation in a cost matrix, and propose a general objective function to adapt the robust training method of Wong & Kolter (2018) to optimize for cost-sensitive robustness. Our experiments on simple MNIST and CIFAR10 models with a variety of cost matrices show that the proposed approach can produce models with substantially reduced cost-sensitive robust error, while maintaining classification accuracy.
Code (1)
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Certifying Joint Adversarial Robustness for Model Ensembles
Deep Neural Networks (DNNs) are often vulnerable to adversarial examples.Several proposed defenses deploy an ensemble of models with the hope that, although the individual models may be vulnerable, an adversary will not …
Adversarial RobustnessmodelBalanced Adversarial Training: Balancing Tradeoffs Between Oversensitivity and Undersensitivity in NLP Models
Traditional (\emph{oversensitive}) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. \emph{Undersensi…
Contrastive LearningNatural Language InferenceParaphrase IdentificationInterpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they bring, adversarial examples are also val…
Adversarial RobustnessDecision MakingSensitivityProvably Cost-Sensitive Adversarial Defense via Randomized Smoothing
As ML models are increasingly deployed in critical applications, robustness against adversarial perturbations is crucial. While numerous defenses have been proposed to counter such attacks, they typically assume that all…
Adversarial DefenseAdversarial Examples for Cost-Sensitive Classifiers
Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the u…