English

Quantifying Assurance in Learning-enabled Systems

Software Engineering 2023-01-11 v1 Artificial Intelligence Machine Learning Systems and Control Systems and Control

Abstract

Dependability assurance of systems embedding machine learning(ML) components---so called learning-enabled systems (LESs)---is a key step for their use in safety-critical applications. In emerging standardization and guidance efforts, there is a growing consensus in the value of using assurance cases for that purpose. This paper develops a quantitative notion of assurance that an LES is dependable, as a core component of its assurance case, also extending our prior work that applied to ML components. Specifically, we characterize LES assurance in the form of assurance measures: a probabilistic quantification of confidence that an LES possesses system-level properties associated with functional capabilities and dependability attributes. We illustrate the utility of assurance measures by application to a real world autonomous aviation system, also describing their role both in i) guiding high-level, runtime risk mitigation decisions and ii) as a core component of the associated dynamic assurance case.

Keywords

Cite

@article{arxiv.2006.10345,
  title  = {Quantifying Assurance in Learning-enabled Systems},
  author = {Erfan Asaadi and Ewen Denney and Ganesh Pai},
  journal= {arXiv preprint arXiv:2006.10345},
  year   = {2023}
}

Comments

Author's pre-print version of manuscript accepted for publication in the Proceedings of the 39th International Conference in Computer Safety, Reliability, and Security (SAFECOMP 2020)