Characterizing Data Point Vulnerability as Average-Case Robustness

Tessa Han, Suraj Srinivas, Himabindu Lakkaraju

Keywords: Trustworthy AI, Deep Learning, Robustness, Data-centric Machine Learning

TL;DR: We consider using average-case robustness for identifying vulnerable data-points, and propose efficient analytical estimators for the same.

Abstract: Studying the robustness of machine learning models is important to ensure consistent model behaviour across real-world settings. To this end, adversarial robustness is a standard framework, which views robustness of predictions through a binary lens: either a worst-case adversarial perturbation exists in the local region around an input, or it does not. However, this binary perspective does not account for the degrees of vulnerability, as data points with a larger number of misclassified examples in their neighborhoods are more vulnerable. In this work, we consider a complementary framework for robustness, called average-case robustness, which measures the fraction of points in a local region that provides consistent predictions. However, computing this quantity is hard, as standard Monte Carlo approaches are inefficient especially for high-dimensional inputs. In this work, we propose the first analytical estimators for average-case robustness for multi-class classifiers. We show empirically that our estimators are accurate and efficient for standard deep learning models and demonstrate their usefulness for identifying vulnerable data points, and well as quantifying robustness bias of models. Overall, our tools provide a complementary view to robustness, improving our ability to characterize model behaviour.

List Of Authors: Han, Tessa and Srinivas, Suraj and Lakkaraju, Himabindu

Code Url: https://github.com/AI4LIFE-GROUP/average-case-robustness

Submission Number: 288