Shreyas Ramakrishna, Hyunjee Jin, Abhishek Dubey, Arun Ramamurthy
Computer Safety, Reliability, and Security 2022
Developing assurance cases for complex cyber-physical systems like autonomous vehicles requires extensive manual effort and expertise in pattern selection and instantiation. This work is significant because it automates the pattern selection process while maintaining traceability to system artifacts. The optimization-based approach finds minimal sets of patterns that provide necessary coverage for assurance arguments.
This paper presents an automated pattern selection workflow for assurance case development in cyber-physical systems. The framework handles the pattern selection problem as a coverage problem using graph analytics and ontology graphs of system artifacts. The approach automates the selection of assurance case patterns and provides mechanisms for their instantiation to develop complete assurance cases for complex systems.
The automated pattern selection workflow was demonstrated on an autonomous vehicle example and showed significant reduction in manual effort compared to traditional approaches. The approach successfully identified required patterns and provided mechanisms for instantiating them with system-specific information. The workflow proved effective for organizing complex assurance arguments while maintaining formal rigor.
@inproceedings{ramakrishna2022assurance,
author = {Ramakrishna, Shreyas and Jin, Hyunjee and Dubey, Abhishek and Ramamurthy, Arun},
booktitle = {Computer Safety, Reliability, and Security},
title = {Automating Pattern Selection for Assurance Case Development for Cyber-Physical Systems},
year = {2022},
address = {Cham},
editor = {Trapp, Mario and Saglietti, Francesca and Spisl{\"a}nder, Marc and Bitsch, Friedemann},
pages = {82--96},
publisher = {Springer International Publishing},
abstract = {Assurance Cases are increasingly being required for regulatory acceptance of Cyber-Physical Systems. However, the ever-increasing complexity of these systems has made the assurance cases development complex, labor-intensive and time-consuming. Assurance case fragments called patterns are used to handle the complexity. The state-of-the-art approach has been to manually select generic patterns from online catalogs, instantiate them with system-specific information, and assemble them into an assurance case. While there has been some work in automating the instantiation and assembly, a less researched area is the automation of the pattern selection process, which takes a considerable amount of the assurance case development time. To close this automation gap, we have developed an automated pattern selection workflow that handles the selection problem as a coverage problem, intending to find the smallest set of patterns that can cover the available system artifacts. For this, we utilize the ontology graphs of the system artifacts and the patterns and perform graph analytics. The selected patterns are fed into an external instantiation function to develop an assurance case. Then, they are evaluated for coverage using two coverage metrics. An illustrative autonomous vehicle example is provided, demonstrating the utility of the proposed workflow in developing an assurance case with reduced efforts and time compared to the manual development alternative.},
contribution = {minor},
isbn = {978-3-031-14835-4},
keywords = {assurance cases, cyber-physical systems, pattern selection, automation, autonomous vehicles}
}