Taxonomy of Machine Learning Safety: A Survey and Primer
This provides a structured framework for enhancing safety in ML systems, particularly for safety-critical domains like autonomous vehicles, but it is incremental as it synthesizes existing research into a taxonomy.
The paper addresses the gap between machine learning research and established safety principles by proposing a Taxonomy of ML Safety, which maps state-of-the-art ML techniques to key engineering safety strategies to improve dependability in open-world applications.
The open-world deployment of Machine Learning (ML) algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities such as interpretability, verifiability, and performance limitations. Research explores different approaches to improve ML dependability by proposing new models and training techniques to reduce generalization error, achieve domain adaptation, and detect outlier examples and adversarial attacks. However, there is a missing connection between ongoing ML research and well-established safety principles. In this paper, we present a structured and comprehensive review of ML techniques to improve the dependability of ML algorithms in uncontrolled open-world settings. From this review, we propose the Taxonomy of ML Safety that maps state-of-the-art ML techniques to key engineering safety strategies. Our taxonomy of ML safety presents a safety-oriented categorization of ML techniques to provide guidance for improving dependability of the ML design and development. The proposed taxonomy can serve as a safety checklist to aid designers in improving coverage and diversity of safety strategies employed in any given ML system.