[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124998-en":3,"doc-seo-124998-105":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},124998,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Safety in Graph Machine Learning - Threats and Safeguards","Graph Machine Learning (Graph ML) has advanced rapidly and is now widely used for tasks on graph-structured data across finance, healthcare, and transportation. Growing evidence shows that, without safety-oriented design, Graph ML models may yield unreliable predictions, limited generalizability, and risks to data confidentiality. In high-stakes settings such as financial fraud detection, these weaknesses can endanger individuals and broader societal trust. This survey reviews reliability, generalizability, and confidentiality through a threat taxonomy spanning model, data, and attack threats.","arXiv :2405 . 11034v1 [ cs .LG] 17 May 2024  \nSafety in Graph Machine Learning: Threats and Safeguards  \nSong Wang, Yushun Dong, Binchi Zhang, Zihan Chen, Xingbo Fu, Yinhan He, Cong Shen, Chuxu Zhang, Nitesh V. Chawla, and Jundong Li  \nAbstract—Graph Machine Learning (Graph ML) has witnessed substantial advancements in recent years. With their remarkable ability to process graph-structured data, Graph ML techniques have been extensively utilized across diverse applications, including critical domains like finance, healthcare, and transportation. Despite their societal benefits, recent research highlights significant safety concerns associated with the widespread use of Graph ML models. Lacking safety-focused designs, these models can produce unreliable predictions, demonstrate poor generalizability, and compromise data confidentiality. In high-stakes scenarios such as financial fraud detection, these vulnerabilities could jeopardize both individuals and society at large. Therefore, it is imperative to prioritize the development of safety-oriented Graph ML models to mitigate these risks and enhance public confidence in their applications. In this survey paper, we explore three critical aspects vital for enhancing safety in Graph ML: reliability, generalizability, and confidentiality. We categorize and analyze threats to each aspect under three headings: model threats, data threats, and attack threats. This novel taxonomy guides our review of effective strategies to protect against these threats. Our systematic review lays a groundwork for future research aimed at developing practical, safety-centered Graph ML models. Furthermore, we highlight the significance of safe Graph ML practicesand suggest promising avenues for further investigation in this crucial area.  \nIndex Terms—Graph Machine Learning, Safety, Reliability, Generalizability, Confidentiality  \n~~ ~~ ✦ ~~ ~~  \n1 INTRODUCTION  \nIn recent years, graph-structured data has become increasingly prevalent across a wide range of real-world applications, including drug discovery [15], traffic forecasting [76], and disease diagnosis [96] . Within these domains, Graph Machine Learning (Graph ML) plays a pivotal role in modeling this data and executing graph-based predictive tasks [83], [187] . However, as the scope of Graph ML applications expands, concerns about their underlying safety issues intensify [37] . Inadequately addressing these issues can result in severe implications, particularly in critical decision-making scenarios [203] . For instance, in financial fraud detection, Graph ML models analyze transaction networks where nodes represent users and edges depict transactions [151] . Susceptibility to shifts in data distribution could erroneously flag legitimate transactions as fraudulent [37] . Additionally, these models may also pose risks to user privacy [124] . Both these safety concerns significantly erode trust in the financial system.  \nDespite growing societal concerns [147], [183], a comprehensive understanding of safety within Graph Machine Learning (Graph ML) is still emerging. This lack of un-  \n• S. Wang, Y. Dong, B. Zhang, Z. Chen, X. Fu, Y. He, C. Shen, and J. Li are with the Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia, USA.  \nE-mails: {sw3wv, yd6eb, epb6gw, brf3rx, xf3av, nee7ne, cong, jun[dong}@virginia.edu](dong}@virginia.edu)  \n• C. Zhang is with the Department of Computer Science, Brandeis University, Waltham, Massachusetts, USA.  \nE-mail: [chuxuzhang@brandeis.edu](chuxuzhang@brandeis.edu)  \n• N. V. Chawla is with the Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA. [E-mail: nchawla@nd.edu](E-mail: nchawla@nd.edu)  \nderstanding impedes researchers and practitioners from systematically identifying and addressing the fundamental safety concerns associated with Graph ML methods. To narrow this gap, our survey seeks to resolve two critical questions:","cbCaigqQWrHEwWGE","https://ap.wps.com/l/cbCaigqQWrHEwWGE","pdf",10057594,1,20,"English","en",105,"# Introduction\n## Safety aspects in Graph ML\n## Reliability\n## Generalizability\n## Confidentiality\n# Threat taxonomy and safeguards\n## Model threats\n## Data threats\n## Attack threats","[{\"question\":\"What safety problems can Graph Machine Learning models face?\",\"answer\":\"Without safety-focused design, Graph ML can produce unreliable predictions, demonstrate poor generalizability, and compromise data confidentiality.\"},{\"question\":\"How does the survey organize safety in Graph ML?\",\"answer\":\"It introduces a taxonomy that categorizes threats under three safety aspects—reliability, generalizability, and confidentiality—and groups them into model threats, data threats, and attack threats.\"},{\"question\":\"Why are reliability and generalizability especially important in real applications?\",\"answer\":\"High-stakes domains require consistent performance: reliability matters when training data quality is low, and generalizability matters when data distributions shift, otherwise legitimate cases may be wrongly flagged or performance may degrade.\"}]","Safety in Graph Machine Learning - Threats and Safeguards | PDF",1785895954,50,{"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},"safety-in-graph-machine-learning-threats-and-safeguards","",{"@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/safety-in-graph-machine-learning-threats-and-safeguards/124998/",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","2026-08-05",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},"What safety problems can Graph Machine Learning models face?","Question",{"text":75,"@type":76},"Without safety-focused design, Graph ML can produce unreliable predictions, demonstrate poor generalizability, and compromise data confidentiality.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the survey organize safety in Graph ML?",{"text":80,"@type":76},"It introduces a taxonomy that categorizes threats under three safety aspects—reliability, generalizability, and confidentiality—and groups them into model threats, data threats, and attack threats.",{"name":82,"@type":73,"acceptedAnswer":83},"Why are reliability and generalizability especially important in real applications?",{"text":84,"@type":76},"High-stakes domains require consistent performance: reliability matters when training data quality is low, and generalizability matters when data distributions shift, otherwise legitimate cases may be wrongly flagged or performance may degrade.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]