Paper ID: 2309.09928

Evaluating Adversarial Robustness with Expected Viable Performance

Ryan McCoppin, Colin Dawson, Sean M. Kennedy, Leslie M. Blaha

We introduce a metric for evaluating the robustness of a classifier, with particular attention to adversarial perturbations, in terms of expected functionality with respect to possible adversarial perturbations. A classifier is assumed to be non-functional (that is, has a functionality of zero) with respect to a perturbation bound if a conventional measure of performance, such as classification accuracy, is less than a minimally viable threshold when the classifier is tested on examples from that perturbation bound. Defining robustness in terms of an expected value is motivated by a domain general approach to robustness quantification.

Submitted: Sep 18, 2023