[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119164-en":3,"doc-seo-119164-105":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},119164,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Understanding IoT Domain Names - Analysis and Classification Using Machine Learning - Research Report","This paper studies domain names of internet servers accessed by IoT devices performing strictly machine-to-machine (M2M) communications, and distinguishes them from domain names contacted by other device types. Domain-name lists are constructed using packet captures of real devices and validated via top-visited website datasets. The work analyzes statistical properties of these lists and trains six machine learning models using Word2vec embeddings, with Random Forest achieving the strongest accuracy, precision, recall, and F1 score. Results support insights for protocol design, network security, and performance monitoring.","Understanding IoT Domain Names: Analysis and Classification Using Machine Learning  \narXiv :2404 . 15068v1 [ cs .NI] 23 Apr 2024  \nIbrahim Ayoub  \nAfnic – Universite´ Paris-Saclay Yvelines, France [ibrahim.ayoub@afnic.fr](ibrahim.ayoub@afnic.fr)  \nMartine S. Lenders Technische Universita¨t Dresden  \nDresden, Germany martine.lenders@tu-dresden.de  \nBenoˆıt Ampeau  \nAfnic Yvelines, France [benoit.ampeau@afnic.fr](benoit.ampeau@afnic.fr)  \nSandoche Balakrichenan  \nAfnic Yvelines, France[sandoche.balakrichenan@afnic.fr](sandoche.balakrichenan@afnic.fr)  \nKinda Khawam  \nUniversite´ de Versailles St-Quentin Versailles, France [kinda.khawam@uvsq.fr](kinda.khawam@uvsq.fr)  \nThomas C. Schmidt HAW Hamburg  \nHamburg, Germany [t.schmidt@haw-hamburg.de](t.schmidt@haw-hamburg.de)  \nMatthias Whlisch  \nTechnische Universita¨t Dresden – Barkhausen Institut Dresden, Germany m.waehlisch@tu-dresden.de  \nAbstract—In this paper, we investigate the domain names of servers on the Internet that are accessed by IoT devices performing machine-to-machine communications. Using machine learning, we classify between them and domain names of servers contacted by other types of devices. By surveying past studies that used testbeds with real-world devices and using lists of top visited websites, we construct lists of domain names of both types of servers. We study the statistical properties of the domain name lists and train six machine learning models to perform the classification. The word embedding technique we use to get the real-value representation of the domain names is Word2vec. Among the models we train, Random Forest achieves the highest performance in classifying the domain names, yielding the highest accuracy, precision, recall, and F1 score. Our work offers novel insights to IoT, potentially informing protocol design and aiding in network security and performance monitoring.  \nIndex Terms—IoT, domain names, machine learning, security  \nI. INTRODUCTION  \nDomain name classification enables detecting both phishing and domain names generated by domain generation algorithms (DGAs) [1]–[3] . Phishing domain names are used by malicious servers that pose as legitimate ones and lure users into providing sensitive information and credentials. On the other hand, DGAs run on malware-infected devices and generate domain names to help the infected devices contact the Command & Control (C&C) servers. The domain name classification techniques could also be applied in the Internet of Things (IoT) environments. IoT devices often need to communicate with servers on the Internet to which they connect using their domain names [4] .  \nIn this paper, we study IoT from a different viewpoint by studying the domain names of the servers on the Internet that IoT devices interact with and classify between them and servers contacted by other types of devices. We are interested in IoT devices that perform strictly machine-tomachine (M2M) communications. The servers such devices contact might be IoT-specific backend servers to which they  \nThis work has been supported by ANR and BMBF within the PIVOT project ([https://pivot-project.info/](https://pivot-project.info/))  \nrelay information, receive commands and updates, or other generic servers not exclusive to IoT.  \nWe compile two lists of domain names. Using packet captures of real devices, initially filtering the traffic of IoT M2M devices, we construct a list of domain names of servers that are contacted by these devices. This list we call IoT M2M Names. The remaining packet captures we use to construct a list of domain names of servers exclusively contacted by other types of devices, never by IoT M2M devices. This list we call Other Names.  \nFor the rest of the paper, we will refer to IoT M2M Devices as IoT M2M Devices and IoT devices that are not M2M, generic devices, and human users as Other Devices.  \nThe end goal is to study the domain names of servers contacted by IoT M2M Devices and classify between them and the domain","cbCaiuVFxQOx0PRU","https://ap.wps.com/l/cbCaiuVFxQOx0PRU","pdf",654748,1,10,"English","en",105,"# Introduction\n## Domain name classification and threat contexts\n## IoT-focused viewpoint and dataset construction\n## Evaluation using prior datasets and top-site lists\n# Methodology\n## Domain-name list construction\n## Preprocessing and statistical analysis\n## Model training and classification evaluation","[{\"question\":\"How do the authors define and separate IoT M2M domain names from other domain names?\",\"answer\":\"They construct one list from packet captures that include only servers contacted by IoT M2M devices (IoT M2M Names), and another list from the remaining traffic never contacted by IoT M2M devices (Other Names).\"},{\"question\":\"What machine learning approach is used for domain name classification?\",\"answer\":\"The paper trains six machine learning models and uses Word2vec to transform domain names into real-valued representations before classification.\"},{\"question\":\"Which model performs best and what metrics are used?\",\"answer\":\"Random Forest achieves the highest performance, delivering the best accuracy, precision, recall, and F1 score among the trained models.\"}]","Understanding IoT Domain Names - Analysis and Classification Using Machine Learning - Research Report | PDF",1785722858,25,{"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},"understanding-iot-domain-names-analysis-and-classification-using-machine-learning-research-report","",{"@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/understanding-iot-domain-names-analysis-and-classification-using-machine-learning-research-report/119164/",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},"How do the authors define and separate IoT M2M domain names from other domain names?","Question",{"text":75,"@type":76},"They construct one list from packet captures that include only servers contacted by IoT M2M devices (IoT M2M Names), and another list from the remaining traffic never contacted by IoT M2M devices (Other Names).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning approach is used for domain name classification?",{"text":80,"@type":76},"The paper trains six machine learning models and uses Word2vec to transform domain names into real-valued representations before classification.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performs best and what metrics are used?",{"text":84,"@type":76},"Random Forest achieves the highest performance, delivering the best accuracy, precision, recall, and F1 score among the trained models.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]