An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models

TL;DR

This paper surveys recent advances in training and certifying robust machine learning models, emphasizing their importance for safety-critical systems and outlining future research directions.

Contribution

It provides a comprehensive overview of formal robustness definitions, training techniques, and certification methods, unifying current approaches and identifying key future challenges.

Findings

Reviewed formal robustness frameworks

Summarized state-of-the-art training methods

Discussed certification techniques

Abstract

In this discussion paper, we survey recent research surrounding robustness of machine learning models. As learning algorithms become increasingly more popular in data-driven control systems, their robustness to data uncertainty must be ensured in order to maintain reliable safety-critical operations. We begin by reviewing common formalisms for such robustness, and then move on to discuss popular and state-of-the-art techniques for training robust machine learning models as well as methods for provably certifying such robustness. From this unification of robust machine learning, we identify and discuss pressing directions for future research in the area.