Adversarial robustness of sparse local Lipschitz predictors

Understand

This work studies the adversarial robustness of parametric functions composed of a linear predictor and a non-linear representation map.

• % that satisfies certain stability condition.
• Our analysis relies on \emph{sparse local Lipschitzness} (SLL), an extension of local Lipschitz continuity that better captures the stability and reduced effective dimensionality of predictors upon local perturbations.
• SLL functions preserve a certain degree of structure, given by the sparsity pattern in the representation map, and include several popular hypothesis classes, such as piece-wise linear models, Lasso and its variants, and deep feed-forward \relu networks.