A Safety Framework for Critical Systems Utilising Deep Neural Networks
Abstract
Increasingly sophisticated mathematical modelling processes from Machine Learning are being used to analyse complex data. However, the performance and explainability of these models within practical critical systems requires a rigorous and continuous verification of their safe utilisation. Working towards addressing this challenge, this paper presents a principled novel safety argument framework for critical systems that utilise deep neural networks. The approach allows various forms of predictions, e.g., future reliability of passing some demands, or confidence on a required reliability level. It is supported by a Bayesian analysis using operational data and the recent verification and validation techniques for deep learning. The prediction is conservative -- it starts with partial prior knowledge obtained from lifecycle activities and then determines the worst-case prediction. Open challenges are also identified.
Cite
@article{arxiv.2003.05311,
title = {A Safety Framework for Critical Systems Utilising Deep Neural Networks},
author = {Xingyu Zhao and Alec Banks and James Sharp and Valentin Robu and David Flynn and Michael Fisher and Xiaowei Huang},
journal= {arXiv preprint arXiv:2003.05311},
year = {2020}
}
Comments
Accepted by SafeComp2020