[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126708-en":3,"doc-seo-126708-105":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},126708,962084925636,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Trustworthy Machine Learning for Anomaly Detection and Computer Vision Applications - Ph.D. Thesis","Technologies based on Artificial Intelligence have become widely adopted thanks to high-performing Machine Learning models that can match or exceed human performance in many application domains. A major limitation remains trustworthiness: AI-enabled systems have caused unintended harm with potentially severe impacts on quality of life, especially in high-stakes settings. This thesis investigates popular models to improve trustworthiness by focusing on interpretability and robustness within Anomaly Detection and Computer Vision, proposing methods to interpret Isolation Forest, enhance robust image classification, analyze adversarial training properties, expose harmful simplicity biases, and design texture-filtering defenses preserving semantic content.","Universit􀀒a degli Studi di Padova  \nDEPARTMENT OF GENERAL PSYCHOLOGY  \nPh.D. School in Brain, Mind and Computer Science Curriculum Computer Science for Societal Challenges and Innovation  \nTrustworthy Machine Learning for Anomaly Detection and Computer Vision  \nApplications  \nSupervisor  \nProf. Gian Antonio Susto  \nCo-Supervisor & Coordinator  \nProf.ssa Anna Spagnolli  \nPh.D. candidate  \nMattia Carletti  \nUniversit􀀒a degli Studi di Padova  \nDEPARTMENT OF GENERAL PSYCHOLOGY  \nPh.D. School in Brain, Mind and Computer Science Curriculum Computer Science for Societal Challenges and Innovation  \nTrustworthy Machine Learning for Anomaly Detection and Computer Vision  \nApplications  \nSupervisor  \nProf. Gian Antonio Susto  \nCo-Supervisor & Coordinator  \nProf.ssa Anna Spagnolli  \nPh.D. candidate  \nMattia Carletti  \nMattia Carletti: Trustworthy Machine Learning for Anomaly Detection and Computer Vision Applications | Ph.D. Thesis, Università degli Studi di Padova.© Copyright 9 January 2023 .  \nUniversità degli Studi di Padova:  \n[www.unipd.it](www.unipd.it)  \nPh.D. School in Brain, Mind and Computer Science:  \nhit.psy.unipd.it/BMCS  \nAcknowledgements  \nFirst of all, I would like to express my gratitude to Prof. Gian Antonio Susto for his enthusiasm in guiding me through this exciting experience.  \nI would also like to mention Prof. Giorgio Quer, who gave me the opportunity to live a wonderful experience in San Diego.  \nI am also grateful to my family and my friends, my pillar of strength.  \nI would like to express a special thanks to Matteo, with whom I spent a great deal of time talking about research and life.  \nA special mention goes to my girlfriend Ortensia for her endless patience and support. She is now probably more expert than me in Machine Learning.  \nPadova, 9 January 2023 M. C.  \nAbstract  \nTechnologies based on Artificial Intelligence (AI) have gained tremendous popularity in the past few years. This is made possible by the fact that Machine Learning models can now achieve amazing performance, even outperforming humans in several application domains. Unfortunately, there is still one fundamental aspect in which humans succeed and machines fail miserably: trustworthiness. Countless cases of unintended harm caused by AI-enabled technologies have been reported and have attracted wide media coverage. While unintentional, the consequences of these events could be devastating and affect our quality of life. Even more so if we consider that AI is being increasingly adopted in sensitive domains to support high-stakes decisions. In light of these observations, the need for Trustworthy AI is particularly pressing.  \nIn this thesis, we profoundly investigate the properties of popular models that have been used for years in academia and industry and provide tools to improve their trustworthiness. The focus is on two specific dimensions in the space of Trustworthy AI, i.e., interpretability and robustness, and on two application domains of great practical interest, i.e. , Anomaly Detection and Computer Vision. In the context of Anomaly Detection, we introduce novel model-specific methods to interpret the Isolation Forest, a popular model in this field, at both the global and local scales. In Computer Vision, we address the problem of robust image classification with Convolutional Neural Networks. We first unveil unknown properties of adversarially-trained models, elucidating inner mechanisms through which robustness against adversarial examples may be enforced by Adversarial Training. We also showcase failure modes related to the simplicity biases induced by Adversarial Training that may be harmful when robust models are deployed in the wild. Finally, we design a novel filtering procedure aimed at removing textures while preserving the image’s semantic content. Such filtering procedure is then exploited to design a defense against adversarial attacks.  \nKeywords: Anomaly Detection, Computer Vision, Deep Learning, Interpretability, Robus","cbCaipcWpYvKwxrS","https://ap.wps.com/l/cbCaipcWpYvKwxrS","pdf",10882132,1,164,"English","en",105,"# Abstract\n# Acknowledgements\n# Keywords\n# Somario","[{\"question\":\"What motivates the need for Trustworthy AI in this thesis?\",\"answer\":\"AI systems have been reported to cause unintended harm, and those consequences can be devastating, particularly as AI is adopted in sensitive, high-stakes domains.\"},{\"question\":\"Which dimensions of Trustworthy AI does the thesis focus on?\",\"answer\":\"The thesis concentrates on interpretability and robustness as two key dimensions of trustworthy AI.\"},{\"question\":\"What approaches are introduced for Anomaly Detection and Computer Vision?\",\"answer\":\"For Anomaly Detection, the thesis introduces model-specific methods to interpret Isolation Forest at global and local scales. For Computer Vision, it studies robust image classification with convolutional neural networks, analyzes adversarial training mechanisms and failure modes, and proposes a texture-filtering defense for adversarial attacks.\"}]","Trustworthy Machine Learning for Anomaly Detection and Computer Vision Applications - Ph.D. Thesis | PDF",1785934337,413,{"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-for-anomaly-detection-and-computer-vision-applications-phd-thesis","",{"@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-for-anomaly-detection-and-computer-vision-applications-phd-thesis/126708/",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 motivates the need for Trustworthy AI in this thesis?","Question",{"text":75,"@type":76},"AI systems have been reported to cause unintended harm, and those consequences can be devastating, particularly as AI is adopted in sensitive, high-stakes domains.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which dimensions of Trustworthy AI does the thesis focus on?",{"text":80,"@type":76},"The thesis concentrates on interpretability and robustness as two key dimensions of trustworthy AI.",{"name":82,"@type":73,"acceptedAnswer":83},"What approaches are introduced for Anomaly Detection and Computer Vision?",{"text":84,"@type":76},"For Anomaly Detection, the thesis introduces model-specific methods to interpret Isolation Forest at global and local scales. For Computer Vision, it studies robust image classification with convolutional neural networks, analyzes adversarial training mechanisms and failure modes, and proposes a texture-filtering defense for adversarial attacks.","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"]