[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127502-en":3,"doc-seo-127502-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},127502,962085662650,"Jiven","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Transfer Assurance for Machine Learning in Autonomous Systems - Proceedings Paper","This paper introduces transfer assurance for machine learning (ML) components used within autonomous systems, focusing on maintaining safety evidence when models are updated after deployment. The authors argue that re-training with new or updated development data can invalidate an existing safety case because even small data changes may alter model behavior and performance. They propose making assurance more proportionate to the change size by reusing fixed parts of the assurance case while re-assessing affected elements. The approach is motivated by the cost and complexity of full re-assessment and by transfer learning ideas.","This is a repository copy of Transfer Assurance for Machine Learning in Autonomous Systems.  \nWhite Rose Research Online URL for this paper:  \n[https://eprints.whiterose.ac.uk/196682/](https://eprints.whiterose.ac.uk/196682/)  \nVersion: Published Version  \nProceedings Paper:  \nPicardi, Chiara, Hawkins, Richard David [orcid.org/0000-0001-7347-3413](orcid.org/0000-0001-7347-3413), Paterson, Colin [orcid.org/0000-0002-6678-3752](orcid.org/0000-0002-6678-3752) et al. (1 more author) (2023) Transfer Assurance for Machine Learning in Autonomous Systems. In: Proceedings of the Workshop on Artificial Intelligence Safety (SafeAI 2023) . SafeAI, 13-14 Feb 2023 CEUR Workshop Proceedings , USA .  \nReuse  \nThis article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence allows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the authors for the original work. More information and the full terms of the licence here: [https://creativecommons.org/licenses/](https://creativecommons.org/licenses/)  \nTakedown  \nIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by  \nemailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request.  \n[eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/)  \nTransfer Assurance for Machine Learning in Autonomous Systems  \nChiara Picardi1,∗ , Richard Hawkins1 , Colin Paterson1 and Ibrahim Habli 1  \n1 University of York, York, UK  \nAbstract  \nThis paper introduces the concept of transfer assurance for Machine Learning (ML) components used as part of an autonomous system (AS) . In previous work we developed the first approach for assuring the safety of ML components such that a compelling safety case can be created for their safe deployment. During operation it may be necessary to update an ML component by re-training the model using new or updated development data. If model re-training is required postdeployment, the safety case that was created for the ML component may no longer be valid, since a new model has been created that can no longer be assured to meet its safety requirements. In particular, the nature of machine learnt components means that one may not be able to predict how even small changes in the development data may affect the model and its performance. As a result, current practice would require that a full assurance assessment is undertaken for the re-learned model, and that a new safety case is created. Given the desirability of updating ML components during operation, we see it as imperative that the assurance process become more proportionate to the size of the change that is made to the model, whilst ensuring that assurance can still be demonstrated. Retraining ML components is known to be a costly and complex process and as such techniques such as transfer learning have been developed which aim to reduce this burden through incremental development. Approaches such as transfer learning provide an inspiration for how the challenge of efficiently assuring updated models could be addressed through understanding which aspects ofa model may have been affected by changes to the development data. We refer to this as transfer assurance, where parts of the assurance case for an ML component can remain fixed whilst other parts are re-assessed.  \nKeywords  \nAssurance, Safety, Machine Learning, Transfer Learning, Deep Learning  \n1. Introduction  \nThe use of ML models promises to revolutionise a number of societally-significant, safety-critical domains including healthcare, transport and defence [1, 2, 3] . Whilst such systems may be reported to exceed human performance [4, 5], their adoption is dependent on establishing justified confidence in the safety of systems not only at development time but also once depl","cbCaimbQplfSBcRu","https://ap.wps.com/l/cbCaimbQplfSBcRu","pdf",290822,1,"English","en",105,"# Introduction\n## Assurance for ML components in autonomous systems\n## Motivation for transfer assurance after model updates\n# Approach and concept of transfer assurance\n## Proportionate assurance via fixed and re-assessed evidence","[{\"question\":\"What problem does transfer assurance address for machine learning in autonomous systems?\",\"answer\":\"It addresses how to keep safety evidence valid when an ML component is updated after deployment, especially when re-training changes the model in ways that may affect safety.\"},{\"question\":\"Why can a safety case become invalid after model re-training?\",\"answer\":\"Because the re-trained model may respond differently to the system and environment, and small changes in development data can lead to uncertain effects on model performance.\"},{\"question\":\"How does transfer assurance aim to reduce re-assurance effort?\",\"answer\":\"It enables parts of the assurance case to remain fixed while only the parts impacted by changes to development data are re-assessed, making the process more proportionate to the modification.\"}]","Transfer Assurance for Machine Learning in Autonomous Systems - Proceedings Paper | PDF",1785939495,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"transfer-assurance-for-machine-learning-in-autonomous-systems-proceedings-paper","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/transfer-assurance-for-machine-learning-in-autonomous-systems-proceedings-paper/127502/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does transfer assurance address for machine learning in autonomous systems?","Question",{"text":74,"@type":75},"It addresses how to keep safety evidence valid when an ML component is updated after deployment, especially when re-training changes the model in ways that may affect safety.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why can a safety case become invalid after model re-training?",{"text":79,"@type":75},"Because the re-trained model may respond differently to the system and environment, and small changes in development data can lead to uncertain effects on model performance.",{"name":81,"@type":72,"acceptedAnswer":82},"How does transfer assurance aim to reduce re-assurance effort?",{"text":83,"@type":75},"It enables parts of the assurance case to remain fixed while only the parts impacted by changes to development data are re-assessed, making the process more proportionate to the modification.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]