[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117805-en":3,"doc-seo-117805-105":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},117805,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Adversarial Robustness in Unsupervised Machine Learning - A Systematic Review","Adversarial Robustness in Unsupervised Machine Learning - A Systematic Review conducts a systematic literature review on robustness issues in unsupervised learning, collecting 86 relevant papers. The review evaluates the landscape of adversarial threats and summarizes defenses and remaining gaps across multiple research questions. Results show research concentrates on privacy attacks with comparatively effective defenses, while many other attack types lack robust and general defensive measures. A structured attack-property model is also proposed to support future research.","arXiv :2306 .00687v 1 [ cs .LG] 1 Jun 2023  \nAdversarial Robustness in Unsupervised Machine Learning: A Systematic Review  \nMATHIAS LUNDTEIGEN MOHUS and JINGYUE LI, NTNU Department of Computer Science, Norway  \nAs the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital. This paper conducts a systematic literature review on the robustness of unsupervised learning, collecting 86 papers. Our results show that most research focuses on privacy attacks, which have effective defenses; however, many attacks lack effective and general defensive measures. Based on the results, we formulate a model on the properties of an attack on unsupervised learning, contributing to future research by providing a model to use.  \nCCS Concepts: • Computing methodologies → Unsupervised learning; • Security and privacy → Software security engineering.  \nAdditional Key Words and Phrases: unsupervised learning, machine learning, adversarial robustness, adversarial attack, systematic literature review  \nACM Reference Format:  \nMathias Lundteigen Mohus and Jingyue Li. 2023. Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review. 1, 1 (June 2023), 38 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 INTRODUCTION  \nAs technologies mature, hardware capabilities increase, and legislation is introduced, adopting machine learning technologies in various applications seems inevitable, with the technology generally divided into three types: Supervised Learning (SL), Reinforcement Learning (RL), and Unsupervised Learning. SL focuses on approaches where the training data is labeled, i.e., a data sample maps to a correct value. A variety of cases use this, e.g., object detection [7], image classification [113], and voice recognition [6] . RL is an approach where the model trains in the working environment, rewarding or punishing the model based on its performance. Use cases for this are bug detection in software [119], computing resource optimization [131], and control of cyber-physical systems [96] . UL performs training of its models without guidance; pure data are used as the basis for training. Use cases for this is data generation [45], e.g., GANs; encoding/decoding [133], e.g., autoencoders , and data clustering [29] .  \nBy its lack of need for guided information, UL can enable more data to be usable. In a world that generates a large amount of data (around 2.5 quintillion bytes each day [46]), methods for using unsupervised data would be invaluable. However, where technology is used, adversaries inevitably attempt to exploit vulnerabilities in these technologies. With the increased use of ML in various fields, it is crucial to explore the adversarial robustness of ML models, particularly the use of UL, as this field has received less focus than supervised and reinforcement learning.  \nAuthors’ address: Mathias Lundteigen Mohus, [mathias.l.mohus@ntnu.no](mathias.l.mohus@ntnu.no); Jingyue Li, [jingyue.li@ntnu.no](jingyue.li@ntnu.no), NTNU Department of Computer Science, Sem  \nSælandsvei 9, Trondheim, Trøndelag, Norway, NO-7491 .  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or toredistribute to lists, [requires prior specific permission and/or a fee. Request permissions from permissions@acm.org](requires prior specific permission and/or a fee. Request permissions from permissions@acm.org).  \n© 2023 Association for Computing","cbCaimOs6zNvvGry","https://ap.wps.com/l/cbCaimOs6zNvvGry","pdf",1769129,1,38,"English","en",105,"# Introduction\n## Unsupervised learning and adversarial motivation\n## Scope and research questions\n## Systematic literature review method and analysis\n## Key results (attack targets and defenses)","[{\"question\":\"What is the main goal of the systematic literature review?\",\"answer\":\"To systematically review adversarial robustness across the full field of unsupervised machine learning, including attack types, defenses, and remaining challenges.\"},{\"question\":\"How many papers are included in the review, and how are they analyzed?\",\"answer\":\"The review identifies 86 relevant papers and applies thematic analysis to summarize findings according to the defined research questions.\"},{\"question\":\"What do the results indicate about defenses for different attacks in unsupervised learning?\",\"answer\":\"Most work addresses privacy attacks with effective defenses, but many other attacks do not have effective and general defensive measures.\"}]","Adversarial Robustness in Unsupervised Machine Learning - A Systematic Review | PDF",1785679659,96,{"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},"adversarial-robustness-in-unsupervised-machine-learning-a-systematic-review","",{"@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/adversarial-robustness-in-unsupervised-machine-learning-a-systematic-review/117805/",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},"What is the main goal of the systematic literature review?","Question",{"text":75,"@type":76},"To systematically review adversarial robustness across the full field of unsupervised machine learning, including attack types, defenses, and remaining challenges.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How many papers are included in the review, and how are they analyzed?",{"text":80,"@type":76},"The review identifies 86 relevant papers and applies thematic analysis to summarize findings according to the defined research questions.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the results indicate about defenses for different attacks in unsupervised learning?",{"text":84,"@type":76},"Most work addresses privacy attacks with effective defenses, but many other attacks do not have effective and general defensive measures.","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"]