[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117868-en":3,"doc-seo-117868-105":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},117868,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Botnet attacks detection in IoT environment using machine learning techniques - noise filtering and IDS evaluation","IoT devices with weak security designs enable botnets that can orchestrate coordinated attacks capable of disrupting entire infrastructures. The work develops an intrusion detection approach using machine learning, addressing dataset purity problems by applying noise-filtering methods such as Repeated Edited Nearest Neighbor (RENN), Encoding Length (Explore), and Decremental Reduction Optimization Procedure 5 (DROP5). Three datasets (IoTID20, N-BaIoT, MedBIoT) are processed with instance and feature reduction, followed by supervised evaluation via Accuracy, Precision, Recall, Specificity, F-Score, and G-Mean. Results show strong performance for RENN and especially DROP5 under clean data, with reduced robustness when noise is injected, and N-BaIoT achieving the best overall accuracy.","Contents lists available at GrowingScience  \nInternational Journal of Data and Network Science  \n[homepage: www.GrowingScience.com/ijds](homepage: www.GrowingScience.com/ijds)  \nBotnet attacks detection in IoT environment using machine learning techniques  \nMousa AL-Akhrasa, Abdulmajeed Alshunaybirb, Hani Omarc and Samah Alhazmib*  \naKing Abdullah II School for Information Technology, The University of Jordan, Amman 11942, Jordan  \nbComputer Science Department, College of Computing and Informatics, Saudi Electronic University, Riyadh 11673, Saudi Arabia cFaculty of Information Technology, Applied Science Private University, Amman, Jordan. MEU Research Unit, Middle East University, Amman, Jordan   \nC H R O N I C L E  \nArticle history:  \nReceived: April 10, 2023  \nReceived in revised format: May 25, 2023  \nAccepted: July 29, 2023  \nAvailable online: July 29, 2023  \nKeywords: IoT Botnet DDoS Mirai Bashlite IDS  \nMachine Learning Noise  \nA B S T R A C T  \nIoT devices with weak security designs are a serious threat to organizations. They are the building blocks of Botnets, the platforms that launch organized attacks that are capable of shutting down an entire infrastructure. Researchers have been developing IDS solutions that can counter such threats, often by employing innovation from other disciplines like artificial intelligence and machine learning. One of the issues that may be encountered when machine learning is used is dataset purity. Since they are not captured from perfect environments, datasets may contain data that could affect the machine learning process, negatively. Algorithms already exist for such problems. Repeated Edited Nearest Neighbor (RENN), Encoding Length (Explore), and Decremental Reduction Optimization Procedure 5 (DROP5) algorithm can filter noises out of datasets. They also provide other benefits such as instance reduction which could help reduce larger Botnet datasets, without sacrificing their quality. Three datasets were chosen in this study to construct an IDS: IoTID20, N-BaIoT and MedBIoT. The filtering algorithms, RENN, Explore, and DROP5 were used on them to filter noise and reduce instances. Noise was also injected and filtered again to assess the resilience of these filters. Then feature optimizations were used to shrink the dataset features. Finally, machine learning was applied on the processed dataset and the resulting IDS was evaluated with the standard supervised learning metrics: Accuracy, Precision, Recall, Specificity, F-Score and G-Mean. Results showed that RENN and DROP5 filtering delivered excellent results. DROP5, in particular, managed to reduce the dataset substantially without sacrificing accuracy. However, when noise got injected, the DROP5 accuracy went down and could not keep up. Of the three dataset, N-BaIoT delivers the best accuracy overall across the learning techniques.  \n© 2023 by the authors; licensee Growing Science, Canada.  \n1. Introduction  \nWith the Internet moving away from being a luxury to a necessity, more devices and appliances are turning into IoT devices. Having the property of being connected made these devices popular amongst their adopters. It allowed their users to control and communicate with them with ease, without the need to be physically present. But such simplicity must have a price, though. Those devices nowadays are increasingly becoming major contributors to a variety of cyberattacks. In the last few years, several Botnet-based Distributed Denial of Service (DDoS) attacks have been seen hitting major services around the world. The DDoS attack on Dyn (Feingold, 2016), which rendered many high-profile websites such as Twitter and GitHuband CNN inaccessible, was caused by IoT devices hijacked by Botnets. Kaspersky, the company behind several securityfocused suites, claimed a jump from 12 million in 2018 to more than 100 million attacks in 2019, on their Botnet honeypots  \n* Corresponding author.  \nE-mail address: [s.alhazmi@seu.edu.sa](s.alhazmi@se","cbCaig1IsmlhMoVD","https://ap.wps.com/l/cbCaig1IsmlhMoVD","pdf",1722467,1,24,"English","en",105,"# Abstract\n# 1. Introduction\n## IoT devices and botnet-driven DDoS threats\n## Intrusion Detection Systems and machine learning approaches\n# Keywords","[{\"question\":\"Why is dataset purity important when using machine learning for botnet attack detection in IoT?\",\"answer\":\"Machine learning can be negatively affected by noise or impurities in collected datasets, because they are rarely gathered from ideal environments. Noise-filtering methods are used to mitigate this issue before training the IDS.\"},{\"question\":\"Which noise filtering algorithms are used in the study and what do they aim to improve?\",\"answer\":\"The study applies RENN, Explore (Encoding Length), and DROP5 to filter noises out of datasets and to reduce instances. This supports training on larger botnet datasets without sacrificing quality.\"},{\"question\":\"How are the resulting intrusion detection models evaluated?\",\"answer\":\"Models trained on processed datasets are assessed using standard supervised learning metrics including Accuracy, Precision, Recall, Specificity, F-Score, and G-Mean. RENN and DROP5 show excellent results on clean data, while performance drops for DROP5 when additional noise is injected.\"}]","Botnet attacks detection in IoT environment using machine learning techniques - noise filtering and IDS evaluation | PDF",1785680071,60,{"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},"botnet-attacks-detection-in-iot-environment-using-machine-learning-techniques-noise-filtering-and-ids-evaluation","",{"@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/botnet-attacks-detection-in-iot-environment-using-machine-learning-techniques-noise-filtering-and-ids-evaluation/117868/",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},"Why is dataset purity important when using machine learning for botnet attack detection in IoT?","Question",{"text":75,"@type":76},"Machine learning can be negatively affected by noise or impurities in collected datasets, because they are rarely gathered from ideal environments. Noise-filtering methods are used to mitigate this issue before training the IDS.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which noise filtering algorithms are used in the study and what do they aim to improve?",{"text":80,"@type":76},"The study applies RENN, Explore (Encoding Length), and DROP5 to filter noises out of datasets and to reduce instances. This supports training on larger botnet datasets without sacrificing quality.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the resulting intrusion detection models evaluated?",{"text":84,"@type":76},"Models trained on processed datasets are assessed using standard supervised learning metrics including Accuracy, Precision, Recall, Specificity, F-Score, and G-Mean. RENN and DROP5 show excellent results on clean data, while performance drops for DROP5 when additional noise is injected.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]