[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117961-en":3,"doc-seo-117961-105":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},117961,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine Learning and Security in Adversarial Settings - Dissertation","Machine Learning and Security in Adversarial Settings investigates how adversaries can manipulate learning systems and how security risks emerge in adversarial environments. The dissertation frames threats such as data poisoning, covert manipulation of model inputs, and robustness limitations when learning from static analysis features. It presents research contributions supported by experiments and publications that assess attack effectiveness, transferability, and evaluation methodology. The work aims to strengthen defenses by improving understanding of adversarial behaviors and the reliability of machine learning security evaluations.","UC Santa Barbara  \nUC Santa Barbara Electronic Theses and Dissertations  \nTitle  \nMachine Learning and Security in Adversarial Settings  \nPermalink  \n[https://escholarship.org/uc/item/70k2159d](https://escholarship.org/uc/item/70k2159d)  \nAuthor  \nAghakhani, Hojjat  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUniversity of California  \nSanta Barbara  \nMachine Learning and Security in Adversarial Settings  \nA dissertation submitted in partial satisfaction of the requirements for the degree  \nDoctor of Philosophy  \nin  \nComputer Science  \nby  \nHojjat Aghakhani  \nCommittee in charge:  \nProfessor Christopher Kruegel, Co-Chair  \nProfessor Giovanni Vigna, Co-Chair  \nProfessor Yu-Xiang Wang  \nThe Dissertation of Hojjat Aghakhani is approved.  \nProfessor Yu-Xiang Wang  \nProfessor Christopher Kruegel, Co-Chair  \nProfessor Giovanni Vigna, Co-Chair  \nMay 2023  \nMachine Learning and Security in Adversarial Settings  \nCopyright © 2023 by  \nHojjat Aghakhani  \nI dedicate this thesis to my beloved parents, who have always been my source of inspiration, motivation, and unwavering support. They made immense sacrifices to provide my sisters and me with the best education possible, and their love and commitment to our success never faltered. Mom and Dad, this work is a small token of my deepest gratitude for everything you  \nhave done for me.  \nAcknowledgements  \nI am deeply grateful to everyone who has been part of my incredible journey and has provided me with invaluable support and encouragement.  \nI want to express my gratitude to my family, friends, and loved ones who have always been there for me. To my parents and sisters, thank you for never losing faith in me and supporting my decisions throughout my journey. To my dear old friends outside the US, thank you for always being close to me despite the distance. To my friends in the US, who have become my family here, thank you for never letting me feel alone. I am grateful to my lab mates for creating a fantastic atmosphere and for their amazing support throughout these years. I also thank my collaborators and co-authors for contributing to my research papers.  \nI owe a debt of gratitude to my high school teacher, Mohammad Hassan Kahe, who ignited my passion for mathematics and set me on my academic path. Last but not least, I am immensely grateful to my advisors, Giovanni Vigna and Christopher Kruegel, for being the best advisors I could have asked for. They have taught me how to be an independent researcher and critical thinker, and their guidance and support have been invaluable throughout my Ph.D. journey.  \nCurriculum Vitæ  \nHojjat Aghakhani  \nEducation  \n2016-2023 Ph.D. in Computer Science, University of California, Santa Barbara.  \n2011-2016 B.S. in Computer Engineering, Sharif University of Technology, Iran.  \nPublications  \n1. Aghakhani, Hojjat, Wei Dai, Andre Manoel, Xavier Fernandes, Anant Kharkar, Christopher Kruegel, Giovanni Vigna, David Evans, Ben Zorn, and Robert Sim. \"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models.\" [https://arxiv.org/abs/2301.02344](https://arxiv.org/abs/2301.02344. Under)[.](https://arxiv.org/abs/2301.02344. Under)[ Under](https://arxiv.org/abs/2301.02344. Under)[ ](https://arxiv.org/abs/2301.02344. Under)Revision at the 44th IEEE Symposium on Security and Privacy 2023 .  \n2. Aghakhani, Hojjat, Thorsten Eisenhofer, Lea Schönherr, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, and Giovanni Vigna. \"VENOMAVE: Clean-Label Poisoning Against Speech Recognition. \" To appear in the IEEE Conference on Secure and Trustworthy Machine Learning, February 2023 .  \n3. van Ede, Thijs, Hojjat Aghakhani, Noah Spahn, Riccardo Bortolameotti, Marco Cova, Andrea Continella, Maarten van Steen, Andreas Peter, Christopher Kruegel, and Giovanni Vigna. \"DeepCASE: Semi-Supervised Contextual Analysis of Security Events. \" In 43rd IEEE Symposium ","cbCaiopetMbvIwZD","https://ap.wps.com/l/cbCaiopetMbvIwZD","pdf",10406348,1,251,"English","en",105,"# Dissertation overview\n## Acknowledgements\n## Curriculum Vitae\n## Education\n## Publications","[{\"question\":\"What core topic does the dissertation focus on?\",\"answer\":\"The dissertation focuses on machine learning and security under adversarial settings, studying how threats affect learning systems and security outcomes.\"},{\"question\":\"What kinds of adversarial threats are discussed in the work?\",\"answer\":\"The listed publications cover adversarial techniques such as covert code poisoning of suggestion models and clean-label poisoning attacks, along with robustness limits in malware classification contexts.\"},{\"question\":\"Where can the dissertation and related information be accessed?\",\"answer\":\"The metadata shows an eScholarship.org permalink for the electronic thesis and dissertation record, including publication details and authorship information.\"}]","Machine Learning and Security in Adversarial Settings - Dissertation | PDF",1785680552,633,{"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},"machine-learning-and-security-in-adversarial-settings-dissertation","",{"@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/machine-learning-and-security-in-adversarial-settings-dissertation/117961/",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 core topic does the dissertation focus on?","Question",{"text":75,"@type":76},"The dissertation focuses on machine learning and security under adversarial settings, studying how threats affect learning systems and security outcomes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What kinds of adversarial threats are discussed in the work?",{"text":80,"@type":76},"The listed publications cover adversarial techniques such as covert code poisoning of suggestion models and clean-label poisoning attacks, along with robustness limits in malware classification contexts.",{"name":82,"@type":73,"acceptedAnswer":83},"Where can the dissertation and related information be accessed?",{"text":84,"@type":76},"The metadata shows an eScholarship.org permalink for the electronic thesis and dissertation record, including publication details and authorship information.","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"]