Adversarially Robust Learning with Unknown Perturbation Sets
We study the problem of learning predictors that are robust to adversarial examples with respect to an unknown perturbation set, relying instead on interaction with an adversarial attacker or access to attack oracles, examining different models for such interactions. We obtain upper bounds on the sample complexity and upper and lower bounds on the number of required interactions, or number of successful attacks, in different interaction models, in terms of the VC and Littlestone dimensions of the hypothesis class of predictors, and without any assumptions on the perturbation set.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Adversarially Robust Learning with Uncertain Perturbation Sets
In many real-world settings exact perturbation sets to be used by an adversary are not plausibly available to a learner. While prior literature has studied both scenarios with completely known and completely unknown pert…
Understanding Adversarially Robust Generalization via Weight-Curvature Index
Despite extensive research on adversarial examples, the underlying mechanisms of adversarially robust generalization, a critical yet challenging task for deep learning, remain largely unknown. In this work, we propose a …
Adversarial RobustnessGeneralization BoundsEfficiently Learning Adversarially Robust Halfspaces with Noise
We study the problem of learning adversarially robust halfspaces in the distribution-independent setting. In the realizable setting, we provide necessary and sufficient conditions on the adversarial perturbation sets und…
Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
Interpreting neural network classifiers using gradient-based saliency maps has been extensively studied in the deep learning literature. While the existing algorithms manage to achieve satisfactory performance in applica…
Adversarially Training for Audio Classifiers
In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and non-targeted adversarial attacks. We firstly show …
Benchmarking