{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:06:50Z","timestamp":1768295210099,"version":"3.49.0"},"reference-count":15,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGKDD Explor. Newsl."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:p>Given the increasing ubiquity of Machine Learning (ML), there is an urgent need for assurance frameworks, particularly in relation to ML-enabled safety critical systems. We begin by describing the process of assurance case construction for conventional safety-critical systems that has been developed by the safety engineering community. Goal Structured Notation (GSN), a graphical approach to assurance case construction, is then briefly described. In the sequel, we describe an existing ML assurance framework that employs GSN, Assurance of Machine Learning for use in Autonomous Systems (AMLAS), which is a six-stage assurance process. AMLAS is then applied to our use-case, namely Autonomous Vehicle (AV), with several of the AMLAS stages described in detail. In particular, the creation and testing activities of the ML assurance stage and the instantiation of the assurance argument are developed. Finally, we make the case for increased interaction between the ML and safety engineering community.<\/jats:p>","DOI":"10.1145\/3787470.3787483","type":"journal-article","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:46:21Z","timestamp":1767228381000},"page":"124-131","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Assuring the Case: A Safety Engineering Approach to AI-Enabled Systems"],"prefix":"10.1145","volume":"27","author":[{"given":"Scot","family":"Davidson","sequence":"first","affiliation":[{"name":"Thales IAS, Belfast, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oseghale","family":"Igene","sequence":"additional","affiliation":[{"name":"CSIT, Belfast, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Miller","sequence":"additional","affiliation":[{"name":"CSIT, Belfast, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Assurance Case Working Group (ACWG). Goal Structuring Notation (GSN) Community Standard Version 3. Technical Report SCSC-141C SCSC May 2021. Accessed: 2024--10--22."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33678-2_26"},{"key":"e_1_2_1_3_1","volume-title":"Integration and evaluation of the advocate, fret, cocosim, and event-b tools on the inspection rover case study. Technical report","author":"Bourbouh H.","year":"2020","unstructured":"H. Bourbouh, M. Farrell, A. Mavridou, and I. Sljivo. Integration and evaluation of the advocate, fret, cocosim, and event-b tools on the inspection rover case study. Technical report, 2020."},{"key":"e_1_2_1_4_1","volume-title":"Where failures may occur in automated driving: a fault tree analysis approach. Journal of cognitive engineering and decision making, 17(2):147--165","author":"Chen K.-T.","year":"2023","unstructured":"K.-T. Chen, H.-Y. W. Chen, A. Bisantz, S. Shen, and E. Sahin. Where failures may occur in automated driving: a fault tree analysis approach. Journal of cognitive engineering and decision making, 17(2):147--165, 2023."},{"key":"e_1_2_1_5_1","volume-title":"Ministry of Defence, 2017","author":"DEF","year":"2024","unstructured":"DEF STAN 00--56. Safety management requirements for defence systems, part 1: Requirements. Technical report, Ministry of Defence, 2017. Retrieved October 24, 2024."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2486788.2487056"},{"key":"e_1_2_1_7_1","volume-title":"Guidance on the assurance of machine learning in autonomous systems (amlas). arXiv preprint arXiv:2102.01564","author":"Hawkins R.","year":"2021","unstructured":"R. Hawkins, C. Paterson, C. Picardi, Y. Jia, R. Calinescu, and I. Habli. Guidance on the assurance of machine learning in autonomous systems (amlas). arXiv preprint arXiv:2102.01564, 2021."},{"key":"e_1_2_1_8_1","first-page":"151","volume-title":"International Conference on Product-Focused Software Process Improvement","author":"J\u00a8ockel L.","year":"2023","unstructured":"L. J\u00a8ockel, M. Kl\u00a8as, J. Gro\u00df, P. Gerber, M. Scholz, J. Eberle, M. Teschner, D. Seifert, R. Hawkins, J. Molloy, et al. Operationalizing assurance cases for data scientists: A showcase of concepts and tooling in the context of test data quality for machine learning. In International Conference on Product-Focused Software Process Improvement, pages 151--158. Springer, 2023."},{"key":"e_1_2_1_9_1","volume-title":"Requirements engineering: processes and techniques","author":"Kotonya G.","year":"1998","unstructured":"G. Kotonya and I. Sommerville. Requirements engineering: processes and techniques. Wiley Publishing, 1998."},{"key":"e_1_2_1_10_1","unstructured":"NASA. Advocate user guide 1.4. Technical report NASA Technical Reports Server (NTRS) May 2022. Accessed: 2024--10--22."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prostr.2020.02.069"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04987-3_28"},{"key":"e_1_2_1_13_1","volume-title":"Safety cases for medical devices and health information technology: involving health-care organisations in the assurance of safety. Health informatics journal, 19(3):165--182","author":"Sujan M. A.","year":"2013","unstructured":"M. A. Sujan, F. Koornneef, N. Chozos, S. Pozzi, and T. Kelly. Safety cases for medical devices and health information technology: involving health-care organisations in the assurance of safety. Health informatics journal, 19(3):165--182, 2013."},{"key":"e_1_2_1_14_1","volume-title":"ETSI, 2025","author":"TS","year":"2025","unstructured":"TS 104 223. Securing artificial intelligence (sai); baseline cyber security requirements for ai models and systems. Technical report, ETSI, 2025. Retrieved October, 2025."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2024.112034"}],"container-title":["ACM SIGKDD Explorations Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787470.3787483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:44:02Z","timestamp":1768265042000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787470.3787483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":15,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12,30]]}},"alternative-id":["10.1145\/3787470.3787483"],"URL":"https:\/\/doi.org\/10.1145\/3787470.3787483","relation":{},"ISSN":["1931-0145","1931-0153"],"issn-type":[{"value":"1931-0145","type":"print"},{"value":"1931-0153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]},"assertion":[{"value":"2025-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}