What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
Machine Learning
2024-09-21 v1 Artificial Intelligence
Software Engineering
Systems and Control
Systems and Control
Abstract
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving safety guarantees is one of the most prominent. In this paper, we first discuss the engineering and research challenges associated with the design and verification of such systems. Then, based on the observation that existing works cannot actually achieve provable guarantees, we promote a two-step verification method for the ultimate achievement of provable statistical guarantees.
Keywords
Cite
@article{arxiv.2307.11784,
title = {What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems},
author = {Saddek Bensalem and Chih-Hong Cheng and Wei Huang and Xiaowei Huang and Changshun Wu and Xingyu Zhao},
journal= {arXiv preprint arXiv:2307.11784},
year = {2024}
}