[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290487-105":59,"doc-detail-290487-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","a-study-of-machine-learning-classifiers-for-botnet-traffic-detection-with-an-imbalanced-dataset-thesis-project-report-group-1005-aalborg-university-electronics-and-it","A Study of Machine Learning classifiers for Botnet Traffic Detection with an Imbalanced Dataset - Thesis Project Report Group 1005 - Aalborg University Electronics and IT","","This thesis investigates the use of machine learning models to classify botnet traffic within an Internet of Things (IoT) network. With IoT devices often limited in computational power, they become vulnerable to botnet exploitation, requiring adaptive detection mechanisms with minimal false positives. Traditional network security approaches struggle to follow botnet attacks that dynamically adjust. The study refines IoT-specific botnet detection models by training on imbalanced datasets, optimizing model performance, and identifying influential traffic features. Five models are trained on a BoT-IoT sample and validated on a newly sampled dataset; the voting classifier combining decision tree and XGBoost on an oversampled dataset achieves the best performance.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-study-of-machine-learning-classifiers-for-botnet-traffic-detection-with-an-imbalanced-dataset-thesis-project-report-group-1005-aalborg-university-electronics-and-it/290487/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-study-of-machine-learning-classifiers-for-botnet-traffic-detection-with-an-imbalanced-dataset-thesis-project-report-group-1005-aalborg-university-electronics-and-it/290487.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the thesis address in IoT networks?","Question",{"text":113,"@type":114},"It targets the classification of botnet traffic in an IoT network, where limited device resources make IoT nodes vulnerable to botnet exploitation.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the study handle the imbalanced dataset issue?",{"text":118,"@type":114},"It trains and evaluates models using techniques to balance classes, and then tests trained models on a newly sampled dataset for validation.",{"name":120,"@type":111,"acceptedAnswer":121},"Which machine learning approach delivers the best results?",{"text":122,"@type":114},"A voting classifier that combines a decision tree and XGBoost trained on an oversampled dataset achieves the most favorable performance.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290487,1789641814,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},5909877438554,"https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272","A Study of Machine Learning classifiers for Botnet Traffic Detection with an Imbalanced Dataset  \nProject Report Group 1005  \nAalborg University Electronics and IT  \nElectronics and IT  \nAalborg University [http://www.aau.dk](http://www.aau.dk)  \nTitle:  \nA Study of Machine Learning classifiers for Botnet Traffic Detection with an Imbalanced Dataset  \nTheme:  \nThesis  \nProject Period:  \nSpring Semester 2024  \nProject Group:  \n1005  \nParticipant(s):  \nKamilla Andersen-Otte Georgi Toshkov Bolgurov  \nSupervisor(s):  \nAshutosh Dhar Dwivedi  \nPage Numbers: 90  \nDate of Completion:  \nMay 30, 2024  \nAbstract:  \nThis thesis investigates the use of machine learning models to classify botnet traffic within an Internet of Things (IoT) network. Given the increasing prevalence of IoT devices in our society, their limited computational power makes them a vulnerable target for botnet exploitation, making advanced detection mechanisms that can adapt to evolving threats with minimal false positives necessary. Traditional methods of network security often fail to adapt to the dynamicaly adjusting nature of botnet attacks, making machine learning, with its ability to learn and detect patterns in data a more effective solution. This study refines and enhances machine learning models specifically tailored for IoT botnet detection by tackling three key questions: ensuring proper pattern recognition through training on imbalanced datasets, optimizing machine learning models for botnet traffic detection in IoT networks, and identifying the most influential network traffic features for detecting potential botnet activities. Five machine learning models - decision tree, random forest, Gaussian Naive Bayes, XGBoost, and a voting classifier-were trained on the BoT-IoT dataset sample, with the feature sets being selected based on both feature correlation and forward and backward selection methods. Addressing the dataset imbalance, different techniques were employed to balancing the classes. The trained models were also tested on a newly sampled dataset to provide performance validation. The results indicated that the voting vlassifier, combining decision tree and XGBoost on an oversampled dataset, achieved the most favorable performance.  \nThe content of this report is freely available, but publication (with reference) may only be pursued due to agreement with the author.  \nContents  \n1 Practical Methods and Approaches 1  \n2 Introduction & Background 4  \n2.1 Introduction ...................................... 4  \n2.1.1 Problem formulation ............................. 5  \n2.2 Background ...................................... 6  \n2.3 State of the art ..................................... 8  \n3 Theory 14  \n3.1 Rationale for choice of machine learning models ................. 14  \n3.2 Feature selection ................................... 18  \n3.3 BoT-IoT dataset .................................... 21  \n4 Experiments 28  \n4.1 Model parameters ................................... 28  \n4.2 Experiment setup ................................... 34  \n4.3 Feature selection ................................... 35  \n4.4 Entropy ......................................... 37  \n4.5 Feature correlation .................................. 46  \n4.6 Wrapper methods ................................... 65  \n5 Interpretation of Results 69  \n5.1 Insights from the Machine Learning Models ................... 69  \n5.2 Insights from the Feature Selection ......................... 71  \n5.3 Limitations of the Study ............................... 74  \n5.4 Future Directions and Recommendations ..................... 75  \n6 Conclusion 79  \nBibliography 85  \nA Appendix a  \nPreface  \nAalborg University May 30, 2024  \nHere is the preface. You should put your signatures at the end of the preface.  \nKamilla Andersen-Otte[kande22@student.aau.dk](kande22@student.aau.dk)  \nGeorgi Toshkov Bolgurov[gbolgu22@student.aau.dk](gbolgu22@student.aau.dk)  \nChapter 1  \nPractical Methods and Approaches  \nThis","cbCaioyjAzJB9vfn","https://ap.wps.com/l/cbCaioyjAzJB9vfn","pdf",4849973,101,"English","# Practical Methods and Approaches\n# Introduction & Background\n## Introduction\n### Problem formulation\n## Background\n## State of the art\n# Theory\n## Rationale for choice of machine learning models\n## Feature selection\n## BoT-IoT dataset\n# Experiments\n## Model parameters\n## Experiment setup\n## Feature selection\n## Entropy\n## Feature correlation\n## Wrapper methods\n# Interpretation of Results\n## Insights from the Machine Learning Models\n## Insights from the Feature Selection\n## Limitations of the Study\n## Future Directions and Recommendations\n# Conclusion\n# Bibliography\n# Appendix","[{\"question\":\"What problem does the thesis address in IoT networks?\",\"answer\":\"It targets the classification of botnet traffic in an IoT network, where limited device resources make IoT nodes vulnerable to botnet exploitation.\"},{\"question\":\"How does the study handle the imbalanced dataset issue?\",\"answer\":\"It trains and evaluates models using techniques to balance classes, and then tests trained models on a newly sampled dataset for validation.\"},{\"question\":\"Which machine learning approach delivers the best results?\",\"answer\":\"A voting classifier that combines a decision tree and XGBoost trained on an oversampled dataset achieves the most favorable performance.\"}]","A Study of Machine Learning classifiers for Botnet Traffic Detection with an Imbalanced Dataset - Thesis Project Report Group 1005 - Aalborg University Electronics and IT | PDF",255]