[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119399-en":3,"doc-seo-119399-105":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},119399,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Analysis of Parallel Pre-Processing of Malware Data for Machine Learning in Python - Thesis/Dissertation","Machine learning-driven malware detection and identification supports stronger computer protection. This thesis studies how malware binaries must be pre-processed before they can be used for learning, especially when intermediate languages evolve and expose diverse opcode generation. Focusing on Python and cloud-based computation, it improves prior Python code by analyzing data-preparation performance across environments to quantify delay and cloud cost impacts. It then builds a dictionary-based system using multiprocessing and coroutines to reduce pre-processing computation time and resources while processing malware datasets efficiently. Results show VM costs depend on time, and multi-process approaches can save time even when speedup is not strictly linear.","1  \nATHABASCA UNIVERSITY  \nANALYSIS OF PARALLEL PRE-PROCESSING OF MALWARE DATA FOR  \nMACHINE LEARNING IN PYTHON  \nBY  \nNELS LARSEN  \nA THESIS/DISSERTATION  \nSUBMITTED TO THE FACULTY OF GRADUATE STUDIES  \nIN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF SCIENCE IN INFORMATION SYSTEMS  \nSCHOOL OF COMPUTING AND INFORMATION SYSTEMS  \nATHABASCA, ALBERTA  \nJULY 2023  \nApproval of Thesis  \nThe undersigned certify that they have read the thesis entitled  \nANALYSIS OF PARALLEL PRE-PROCESSING OF MALWARE DATA FOR  \nMACHINE LEARNING IN PYTHON  \nSubmitted by  \nNels Larsen  \nIn partial fulfillment of the requirements for the degree of  \nMaster of Science in Information Systems  \nThe thesis examination committee certifies that the thesis  \nand the oral examination is approved  \nSupervisor:  \nDr. Qing Tan  \nAthabasca University  \nCommittee Member:  \nDr. Harris Wang  \nAthabasca University  \nExternal Examiner:  \nDr. Ali Dewan  \nAthabasca University  \nAugust 9, 2023  \n1 University Drive, Athabasca, AB, T9S 3A3 Canada Toll-free (CAN/U.S.) 1.800.788.9041 ex. 6821  \nfgs@athabascau.ca | fgs.athabascau.ca | athabascau.ca  \n2  \nAbstract  \nMachine learning-driven malware detection and identification helps protect computers.  \nThis thesis initially aimed to develop a machine-learning malware detection solution by utilizing intermediate languages so that malware studies can ignore specific hardware and operating systems while effectively using machine learning to detect and classify malware. Reduction of instruction set size lowers computing costs when using machine learning. Malware must be processed for machine learning before it can be studied. The evolution of tools and diversity of intermediate languages requires that binaries must be processed in a way that order to explore opportunities to optimize based on diverse types of opcode generation from binaries.  \nSince Python programming language is a popular choice for machine learning and much more machine-learning computation has taken place on the cloud, this research aimed to improve existing Python code to detect malware on the cloud platform. However, data preparation is an essential step for all machine-learning processing. This research focused on better malware processing by examining previous research's code. Optimization recommendations of this research can be generalized to applications outside of malware research but are focused on what a malware database would require for processing and would be unsuitable for broad applications without limitations. The first part of the research identified how the data preparation can delay research and incur costs when using cloud infrastructure through the analysis of measurement of performance in different environments.  \nThe second part of the thesis research has created a dictionary system that includes multi-process and coroutines to address the idea of reducing computing costs. This system functions as a single dictionary to optimize time to gain efficiency and save the machine learning pre-processing computation costs. Understanding how to alter parallel processing allowed for the reduction in costs and time for both academic research and commercial practices. The  \n3  \nimplementation of this dictionary system addresses how to process datasets specific to malware research. The dictionary system demonstrates further knowledge in dealing with parallel processing associated with the high processing requirements and high size of this dataset.  \nA standard cost model for cloud infrastructure is to charge by time. This thesis research shows that a single-threaded dictionary takes more time but fewer resources than a parallel processing solution used with dictionaries. As Python's internal multithreading mechanisms can slow execution time, this research found that some wasteful types of concurrent processing can save time. Because virtual machine (VM) costs are primarily time-based, this research has proven that a multi-process di","cbCaikEnfXcKJ5DN","https://ap.wps.com/l/cbCaikEnfXcKJ5DN","pdf",1675429,1,106,"English","en",105,"# Chapter 1 Introduction\n## Background and Motivation\n## Research Purposes\n## Research Objectives and Research Problem\n## Research Findings and Contributions\n## Research Limitations and Delimitations\n## Definition of Terms\n# Chapter 2 Literature Review\n## Introduction to Malware","[{\"question\":\"What is the main goal of this thesis on malware analysis?\",\"answer\":\"The thesis aims to improve machine-learning malware detection by analyzing and optimizing parallel pre-processing of malware data in Python, particularly for cloud-based computation.\"},{\"question\":\"Why is pre-processing critical for machine learning malware studies?\",\"answer\":\"Malware data must be transformed before it can be used for machine learning. Changes in intermediate languages also require processing that can capture diverse opcode generation opportunities for optimization.\"},{\"question\":\"How does the dictionary system reduce cloud processing costs?\",\"answer\":\"It uses multiprocessing and coroutines to optimize pre-processing time and efficiency, targeting lower machine-learning pre-processing computation costs for malware datasets.\"}]","Analysis of Parallel Pre-Processing of Malware Data for Machine Learning in Python - Thesis/Dissertation | PDF",1785724097,267,{"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},"analysis-of-parallel-pre-processing-of-malware-data-for-machine-learning-in-python-thesisdissertation","",{"@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/analysis-of-parallel-pre-processing-of-malware-data-for-machine-learning-in-python-thesisdissertation/119399/",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},"What is the main goal of this thesis on malware analysis?","Question",{"text":75,"@type":76},"The thesis aims to improve machine-learning malware detection by analyzing and optimizing parallel pre-processing of malware data in Python, particularly for cloud-based computation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is pre-processing critical for machine learning malware studies?",{"text":80,"@type":76},"Malware data must be transformed before it can be used for machine learning. Changes in intermediate languages also require processing that can capture diverse opcode generation opportunities for optimization.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the dictionary system reduce cloud processing costs?",{"text":84,"@type":76},"It uses multiprocessing and coroutines to optimize pre-processing time and efficiency, targeting lower machine-learning pre-processing computation costs for malware datasets.","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"]