Adversarial Examples as an Input-Fault Tolerance Problem

Angus Galloway
Anna Golubeva
Graham William Taylor
NeurIPS Workshop on Security in Machine Learning (2018)

Abstract

We analyze the adversarial examples problem in terms of a model’s fault tolerance
with respect to its input. Whereas previous work focuses on arbitrarily strict threat
models, i.e., -perturbations, we consider arbitrary valid inputs and propose an
information-based characteristic for evaluating tolerance to diverse input faults.

Research Areas