[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118317-en":3,"doc-seo-118317-105":30,"detail-sidebar-cat-0-en-105":91},{"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":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118317,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Trustworthy machine learning in the context of security and privacy","Artificial intelligence-based algorithms are increasingly used in critical domains such as healthcare and autonomous vehicles, where security and privacy weaknesses can undermine both safety and compliance. The work surveys security, privacy, and defense techniques to strengthen machine learning trustworthiness, with emphasis on federated learning. It explains how federated learning connects security and privacy goals, supports privacy requirements without sharing data, and discusses future challenges and cross-field dependencies. The paper also outlines research directions toward unified solutions combining security, privacy, and trustworthy AI.","International Journal of Information Security [https://doi.org/10.1007/s10207-024-00813-3](https://doi.org/10.1007/s10207-024-00813-3)  \nTrustworthy machine learning in the context of security and privacy  \nRamesh Upreti1,2 · Pedro G. Lind1,2 · Ahmed Elmokashfi3 · Anis Yazidi1,2  \n© The Author(s) 2024  \nAbstract  \nArtificial intelligence-based algorithms are widely adopted in critical applications such as healthcare and autonomous vehicles. Mitigating the security and privacy issues of AI models, and enhancing their trustworthiness have become of paramount importance. We present a detailed investigation of existing security, privacy, and defense techniques and strategies to make machine learning more secure and trustworthy. We focus on the new paradigm of machine learning called federated learning, where one aims to develop machine learning models involving different partners (data sources) that do not need to share data and information with eachother. In particular, we discuss how federated learning bridges security and privacy, how it guarantees privacy requirements of AI applications, and then highlight challenges that need to be addressed in the future. Finally, after having surveyed the high-level concepts of trustworthy AI and its different components and identifying present research trends addressing security, privacy, and trustworthiness separately, we discuss possible interconnections and dependencies between these three fields. All in all, we provide some insight to explain how AI researchers should focus on building a unified solution combining security, privacy, and trustworthy AI in the future.  \nKeywords Machine learning · Federated learning · Trustworthiness · Security · Privacy  \n1 Introduction and motivation  \nDevelopment and investment in artificial intelligence (AI) technology is advancing at a rapid pace. AI has penetrated almost all life sectors from healthcare, and finance to space research. Despite the exponential adoption of AI-based solutions, several studies have unveiled some security and privacy vulnerabilities associated with AI systems [1–3] . In addition to this, some regulatory measures, namely the recent General Data Protection Regulation (GDPR), enforced by the Euro-  \nB Anis Yazidi[anis.yazidi@oslomet.no](anis.yazidi@oslomet.no)  \nRamesh Upreti  \n[rameshupreti321@gmail.com](rameshupreti321@gmail.com)  \nPedro G. Lind  \n[pedro.lind@oslomet.no](pedro.lind@oslomet.no)  \nAhmed Elmokashfi  \n[ahmed@simula.no](ahmed@simula.no)  \n1 Department of Computer Science, OsloMet Oslo Metropolitan University, Oslo, Norway  \n2 NordSTAR-Nordic Center for Sustainable and Trustworthy AI Research, Oslo, Norway  \n3 Simula Metropolitan Center for Digital Engineering, Oslo, Norway  \npean Union, the California Consumer Privacy Act (CCPA), enforced by the state of California in the USA and many other legislations introduced strong policies to ensure user data protection, preserve privacy and guarantee the security of data used in AI solutions.  \nConsequently, for proper regulation policies, the requirements of security and privacy-proof AI solutions have become of utmost importance and mandatory in today’s AI world.  \nIn traditional programming settings, the programmer knows how to generate output by creating rules or logic procedures working on input space. The success of the program (algorithm) is completely dependent on the ability of the programmer to write the code following the needed logic structure. This seems to be possible when the logic that maps the input to the output can be written using a sequence of conditional sentences (if-then statements) . However, complex programming tasks such as face recognition involve rules and logic procedures that are impossible for humans to code because of two main issues. First, the complexity of the logic behind the programming tasks, and second, the fact that these tasks are typically performed using latent knowledge in our mind that is impossible to express in words and write u","cbCaip1gFjIdUOUH","https://ap.wps.com/l/cbCaip1gFjIdUOUH","pdf",1596747,1,28,"English","en",105,"# Introduction and motivation\n## Machine learning adoption and emerging vulnerabilities\n## Programming limits and the motivation for ML\n## Learning paradigms: supervised learning, unsupervised learning, and reinforcement learning","[{\"question\":\"Why are security and privacy important for trustworthy machine learning?\",\"answer\":\"Because AI is adopted in critical applications, existing security and privacy vulnerabilities can directly impact user data protection, confidentiality, and overall security of AI systems.\"},{\"question\":\"How does federated learning help bridge security and privacy in AI?\",\"answer\":\"Federated learning enables model development across multiple partners without requiring direct sharing of data, supporting privacy requirements while still enabling collaborative learning.\"},{\"question\":\"What future challenges does the work highlight for federated and trustworthy AI?\",\"answer\":\"It discusses challenges that still need to be addressed to ensure strong privacy guarantees and to connect security, privacy, and trustworthiness into coherent solutions.\"}]","Trustworthy machine learning in the context of security and privacy | PDF",1785683030,71,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"trustworthy-machine-learning-in-the-context-of-security-and-privacy","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/trustworthy-machine-learning-in-the-context-of-security-and-privacy/118317/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are security and privacy important for trustworthy machine learning?","Question",{"text":75,"@type":76},"Because AI is adopted in critical applications, existing security and privacy vulnerabilities can directly impact user data protection, confidentiality, and overall security of AI systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does federated learning help bridge security and privacy in AI?",{"text":80,"@type":76},"Federated learning enables model development across multiple partners without requiring direct sharing of data, supporting privacy requirements while still enabling collaborative learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What future challenges does the work highlight for federated and trustworthy AI?",{"text":84,"@type":76},"It discusses challenges that still need to be addressed to ensure strong privacy guarantees and to connect security, privacy, and trustworthiness into coherent solutions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]