[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120158-en":3,"doc-seo-120158-105":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},120158,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","MALWARE DETECTION USING OPCODES AND MACHINE LEARNING - Thesis","The continuous growth of digital systems, central to everyday life, has shifted attention toward securing these infrastructures under fast-evolving cyberattacks. Malware attacks—ranging from viruses and worms to ransomware and spyware—threaten availability, integrity, and confidentiality. Signature-based anti-malware techniques struggle to identify newly modified variants. This thesis examines opcode traces of executed instructions combined with machine learning to train classification models capable of detecting malware during application runtime.","MALWARE DETECTION USING OPCODES AND  \nMACHINE LEARNING  \nMARTÍ ALONSO GARCÍA  \nThesis supervisor  \nJUAN JOSÉ COSTA PRATS (Department of Computer Architecture)  \nThesis co-supervisor  \nENRIC MORANCHO LLENA (Department of Computer Architecture)  \nDegree  \nBachelor's Degree in Informatics Engineering (Computer Engineering)  \nBachelor's thesis  \nFacultat d'Informàtica de Barcelona (FIB) Universitat Politècnica de Catalunya (UPC) -BarcelonaTech  \n01/07/2024  \nAcknowledgments  \nI would like to state my honest gratitude to everyone who has helped me during this project. Specifically, I am immensely grateful to Juan Jos´e Costa and Enric Morancho, for their support, advice and supervision. I am also deeply thankful to Ramon Canal, Beatriz Otero, and David Andreu from the VITAMIN-V project, for their assistance and insights.  \nFinally, I would like to express my sincere appreciation to my friends and family, for their support throughout my academic career.  \nAbstract  \nThe use of digital systems has not stopped growing over the years, and being a critical aspect of our everyday lives, the focus is shifting towards the security of those systems. The constant threat of fast-paced evolving cyberattacks to digital infrastructure requires the development of new protection strategies to effectively defend against them. One type of such cyberattacks is malware attacks, which range from viruses and worms to ransomware and spyware. Traditional anti-malware techniques use signature-based approaches, which are not effective enough when detecting new or altered versions of malware. Recent advances in this field of study have proven that machine learning approaches are capable of detecting malware attacks. This study analyzes and validates the use of opcode traces of executed instructions and machine learning to train classification models that are able to detect malware attacks during the runtime of an application.  \nResumen  \nEl uso de sistemas digitales no ha parado de crecer a lo largo de los a˜nos, y al ser un aspecto cr´ıtico de nuestro d´ıa a d´ıa, se est´a incrementando el enfoque en la seguridad de estos sistemas. Los ciberataques evolucionan r´apidamente y su constante amenaza hacia la infraestructura digital requiere el desarrollo de nuevas medidas de protecci´on para defenderse eficazmente de ellos. Un tipo de estos ciberataques son los ataques malware, los cuales pueden ser desde virus y worms hasta ransomware y spyware. Last´ecnicas tradicionales para combatir malware utilizan enfoques basados en firmas, los cuales no son lo suficientemente efectivos para detectar nuevas versiones de programas maliciosos. Recientes avances en este campo de estudio han demostrado que enfoques deaprendizaje autom´atico son capaces de detectar ataques malware. Este estudio analiza y valida el uso de trazas de c´odigos de operaci´on de las instrucciones ejecutadas y de aprendizaje autom´atico para entrenar modelos de clasificaci´on que puedan detectarataques malware en tiempo de ejecuci´on de una aplicaci´on.  \nResum  \nL’´us de sistemes digitals no ha parat de cr´eixer al llarg dels anys, i en ser un aspectecr´ıtic del nostre dia a dia, s’est`a incrementant l’enfocament en la seguretat d’aquests sistemes. Els ciberatacs evolucionen r`apidament i la seva constant amena¸ca cap a la infraestructura digital requereix el desenvolupament de noves mesures de protecci´o per defensar-se efica¸cment d’ells. Un tipus d’aquests ciberatacs s´on els atacs malware, els quals poden ser des de virus i worms fins a ransomware i spyware. Les t`ecniques tradicionals per combatre malware utilitzen enfocaments basats en signatures, els quals nos´on prou efectius per detectar noves versions de programes maliciosos. Recents aven¸cosen aquest camp d’estudi han demostrat que enfocaments d’aprenentatge autom`atic s´oncapa¸cos de detectar atacs malware. Aquest estudi analitza i valida l’´us de traces decodis d’operaci´o de les instruccions executades i d’aprenentatge autom`atic per ","cbCaiu6FZsc0FWAf","https://ap.wps.com/l/cbCaiu6FZsc0FWAf","pdf",1205837,1,87,"English","en",105,"# Context and scope\n## Introduction and contextualization\n## Justification\n## Scope\n## Project management","[{\"question\":\"Why do signature-based anti-malware techniques have limitations?\",\"answer\":\"They rely on known signatures, making them insufficient for detecting newly created or modified malicious program variants.\"},{\"question\":\"What signals does the study use for malware detection?\",\"answer\":\"The study uses opcode traces of executed instructions during application runtime.\"},{\"question\":\"How does machine learning contribute to the proposed approach?\",\"answer\":\"Machine learning trains classification models on the extracted opcode-trace data to enable malware detection while the application runs.\"}]","MALWARE DETECTION USING OPCODES AND MACHINE LEARNING - Thesis | PDF",1785728484,219,{"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},"malware-detection-using-opcodes-and-machine-learning-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/malware-detection-using-opcodes-and-machine-learning-thesis/120158/",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","2026-08-03",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},"Why do signature-based anti-malware techniques have limitations?","Question",{"text":75,"@type":76},"They rely on known signatures, making them insufficient for detecting newly created or modified malicious program variants.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What signals does the study use for malware detection?",{"text":80,"@type":76},"The study uses opcode traces of executed instructions during application runtime.",{"name":82,"@type":73,"acceptedAnswer":83},"How does machine learning contribute to the proposed approach?",{"text":84,"@type":76},"Machine learning trains classification models on the extracted opcode-trace data to enable malware detection while the application runs.","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"]