Curating Naturally Adversarial Datasets for Learning-Enabled Medical Cyber-Physical Systems

TL;DR

This paper introduces a method to create datasets with naturally occurring adversarial examples in healthcare, enabling more realistic robustness evaluation of deep learning models beyond synthetic attacks.

Contribution

It proposes a novel approach to curate naturally adversarial datasets using probabilistic labels and adversarial ordering, addressing limitations of synthetic adversarial robustness testing.

Findings

Effective generation of naturally adversarial datasets across multiple case studies

Demonstrated statistical validity of the curated datasets

Improved robustness evaluation for medical time-series models

Abstract

Deep learning models have shown promising predictive accuracy for time-series healthcare applications. However, ensuring the robustness of these models is vital for building trustworthy AI systems. Existing research predominantly focuses on robustness to synthetic adversarial examples, crafted by adding imperceptible perturbations to clean input data. However, these synthetic adversarial examples do not accurately reflect the most challenging real-world scenarios, especially in the context of healthcare data. Consequently, robustness to synthetic adversarial examples may not necessarily translate to robustness against naturally occurring adversarial examples, which is highly desirable for trustworthy AI. We propose a method to curate datasets comprised of natural adversarial examples to evaluate model robustness. The method relies on probabilistic labels obtained from automated weakly-supervised labeling that combines noisy and cheap-to-obtain labeling heuristics. Based on these labels, our method adversarially orders the input data and uses this ordering to construct a sequence of increasingly adversarial datasets. Our evaluation on six medical case studies and three non-medical case studies demonstrates the efficacy and statistical validity of our approach to generating naturally adversarial datasets