[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118659-en":3,"doc-seo-118659-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},118659,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Machine Learning for Phishing Website Detection","Phishing attacks are increasing and phishing websites are widespread, exposing the fragility of security mechanisms that rely on blocklists. This dissertation studies machine learning–based Phishing Website Detectors (PWD) and how ML can detect weak data patterns that humans miss. It investigates (i) adversarial evasion attacks against ML-PWD with realistic attacker costs, (ii) how users perceive phishing webpages modified with adversarial perturbations, and (iii) differences between Chinese and Western ML-PWD in multilingual settings. Results highlight practical security gaps and implications for future defenses.","UNIVERSITY OF PADUA  \nPH. D. SCHOOL IN BRAIN, MIND AND COMPUTER SCIENCE Curriculum in Computer Science and Innovation for Societal Challenges  \nXXXVI Cycle  \nMachine Learning for Phishing Website  \nDetection  \nCandidate: Ying YUAN  \nSupervisor: Prof. Mauro CONTI University of Padua  \nCo-Supervisor: Prof. Anna Spagnolli University of Padua  \niii  \nAcknowledgements  \nFirst of all, I would like to give my heartfelt thanks to my supervisor, Prof. Mauro Conti, for his invaluable instruction, inspiration and patience. He introduced me to many nice professors and gave me a chance to work with them, including Prof. Giovanni Apruzzese and Prof. Gang Wang. It’s my great honour to join SPRITZ group and meet wonderful colleagues here, including Luca Pajola, Federico Turrin, Stefano Cecconello, Pier Paolo Tricomi, Alessandro Visintin and Jiaxin Li. Also, I would like to express my gratitude to everyone at 732 for the happy time we had together. I had an unforgettable time in Italy. In addition, I must thank my parents, my younger brother and my friend Yalan Wang, I can not live abroad without their support and inspiration. Last but not least, a special thanks to Prof. Giovanni Apruzzese, for his kindness, illuminating guidance and profound knowledge. It was quite inspiring and exciting to work with him. I am really grateful to all those who devote much time to reading this thesis and give me much advice, which will benefit me in my later studies.  \nv  \nAbstract  \nPhishing attacks are on the rise and phishing websites are everywhere, denoting the brittleness of security mechanisms reliant on blocklists. Prior work proposed enhancing Phishing Website Detectors (PWD) to mitigate this threat with data-driven techniques powered by Machine Learning (ML) . The main advantage of ML models is their intrinsic ability of noticing weak patterns in the data that are overlooked by a human, and then leveraging such patterns to devise ‘flexible’ detectors that can counter even adaptive attackers.  \nThis dissertation addresses three significant aspects arising from the interaction between machine learning and phishing website detection: (i) Adversarial attack for machine learning-based phishing website detection (ML-PWD),(ii) User perceptions of Phishing webpages, and (iii) Phishing website detection in multi-language environment (i.e., Chinese and Western)  \nThe first part presents the security of ML-based phishing website detection. Existing literature on adversarial Machine Learning (ML) focuses either on showing attacks that break every ML model, or defenses that withstand most attacks. Unfortunately, little consideration is given to the actual cost of the attack or the defense. We formalize the “evasion-space\" in which an adversarial perturbation can be introduced to fool a ML-PWD and propose a realistic threat model describing evasion attacks against ML-PWD that are cheap to stage. Our contribution paves the way for a much-needed re-assessment of adversarial attacks against ML systems for cybersecurity. The second part of the dissertation presents a study to understand user perceptions of phishing and adversarial phishing webpages. Adversarial phishing webpages containing perturbations can easily fool ML-based PWD, but it remains uncertain whether these perturbations could equally deceive the real targetend users. Our study indicates adversarial phishing webpages containing typos are more likely to be perceived by users. The third-and last-part of the dissertation reveals the gap between Chinese and Western ML-based PWD, aiming to urge that future work in PWD should take into account the applicability of multilingual environments and pave the way for PWD systems that can protect users having different backgrounds.  \nvii  \nContents  \nAbstract  \n1 Introduction  \n1. 1 Research Motivation and Contribution . . . . . . . . . . . . . . . . . . .  \n1.1. 1 Publications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  \nI Adversarial attack for mach","cbCairHKMvOSljer","https://ap.wps.com/l/cbCairHKMvOSljer","pdf",7381780,1,169,"English","en",105,"# Introduction\n## Research Motivation and Contribution\n## Publications\n# Adversarial attack for learning-based phishing website detection\n# SpacePhish: The Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learning\n## Background and Motivation\n## The Evasion-space of Adversarial Attacks against ML-PWD\n## Proposed Realistic Threat Model\n## Evaluation\n## Results and Discussion\n## Related Work\n## Conclusions\n## Pragmatic Use-Case\n## Threat Model: Considerations\n## Experiments: Considered Attacks","[{\"question\":\"What problem does this dissertation address in phishing website detection?\",\"answer\":\"It addresses the rising prevalence of phishing websites and the brittleness of defenses that depend on blocklists. It focuses on how machine learning–based PWD can detect subtle patterns and how adversaries can evade them.\"},{\"question\":\"How does the work model adversarial attacks against ML-based PWD?\",\"answer\":\"It formalizes the “evasion-space” where adversarial perturbations can fool ML-PWD, and proposes a realistic threat model for evasion attacks with low staging cost.\"},{\"question\":\"What does the dissertation find about user perceptions and multilingual environments?\",\"answer\":\"It shows that adversarial phishing webpages containing typos are more likely to be perceived by users, and it identifies a gap between Chinese and Western ML-PWD. The findings motivate future work to account for multilingual applicability.\"}]","Machine Learning for Phishing Website Detection | PDF",1785684777,426,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-for-phishing-website-detection","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-for-phishing-website-detection/118659/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does this dissertation address in phishing website detection?","Question",{"text":76,"@type":77},"It addresses the rising prevalence of phishing websites and the brittleness of defenses that depend on blocklists. It focuses on how machine learning–based PWD can detect subtle patterns and how adversaries can evade them.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the work model adversarial attacks against ML-based PWD?",{"text":81,"@type":77},"It formalizes the “evasion-space” where adversarial perturbations can fool ML-PWD, and proposes a realistic threat model for evasion attacks with low staging cost.",{"name":83,"@type":74,"acceptedAnswer":84},"What does the dissertation find about user perceptions and multilingual environments?",{"text":85,"@type":77},"It shows that adversarial phishing webpages containing typos are more likely to be perceived by users, and it identifies a gap between Chinese and Western ML-PWD. The findings motivate future work to account for multilingual applicability.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]