Adversarial Risk And Robustness: General Definitions And Implications For The Uniform Distribution

Authors:
Dimitrios Diochnos University of Virginia
Saeed Mahloujifar University of Virginia
Mohammad Mahmoody University of Virginia

Introduction:

The authors study adversarial perturbations when the instances are uniformly distributed over {0,1}^n.

Abstract:

We study adversarial perturbations when the instances are uniformly distributed over {0,1}^n. We study both "inherent" bounds that apply to any problem and any classifier for such a problem as well as bounds that apply to specific problems and specific hypothesis classes.

You may want to know: