RETHINKING ROBUSTNESS IN MACHINE LEARNING: USE OF GENERATIVE ADVERSARIAL NETWORKS FOR ENHANCED ROBUSTNESS.

Abstract

Machine learning (ML) is increasingly being used in real-world applications, so understanding the uncertainty and robustness of a model is necessary to ensure performance in practice. This paper explores approximations for robustness which can meaningfully explain the behavior of any black box model. Starting with a discussion on components of a robust model this paper offers some techniques based on the Generative Adversarial Network (GAN) approach to improve the robustness of a model. The study concludes that a clear understanding of robust models for ML allows to improve information for practitioners, and helps to develop tools that assess the robustness of ML. Also, ML tools and libraries could benefit from a clear understanding on how information should be presented and how these tools are used.