[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123988-en":3,"doc-seo-123988-105":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},123988,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts","IoT device identification is essential for network monitoring, security enforcement, and inventory tracking, yet common approaches centered on deep packet inspection create privacy risks and add computational overhead. Existing methods also downplay wireless channel dynamics, which distort the reliability of layer-2 features in real deployments. This work uses the latency of probe-response packet exchanges, termed device latency, as the primary identification feature, and models channel effects via an accumulation score for machine-learning training. Experiments in real-world scenarios show F1 above 97% despite channel dynamics, versus about 75% when these effects are ignored.","Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts  \nBhagyashri Tushir, Vikram K Ramanna, Yuhong Liu, Behnam Dezfouli  \nInternet of Things Research Lab, Department of Computer Science and Engineering, Santa Clara University, USA {btushir, vramanna, yhliu, [bdezfouli](bdezfouli}@scu.edu)[}](bdezfouli}@scu.edu)[@scu.edu](bdezfouli}@scu.edu)  \narXiv :2405 . 17442v1 [ cs .NI] 15 May 2024  \nAbstract—Identifying IoT devices is crucial for network monitoring, security enforcement, and inventory tracking. However, most existing identification methods rely on deep packet inspection, which raises privacy concerns and adds computational complexity. More importantly, existing works overlook the impact of wireless channel dynamics on the accuracy of layer-2 features, thereby limiting their effectiveness in real-world scenarios. In this work, we define and use the latency of specific probe-response packet exchanges, referred to as ”device latency,” as the main feature for device identification. Additionally, we reveal the critical impact of wireless channel dynamics on the accuracy of device identification based on device latency. Specifically, this work introduces ”accumulation score” as a novel approach to capturing fine-grained channel dynamics and their impact on device latency when training machine learning models. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification, even amidst wireless channel dynamics, a significant improvement over the 75% F1 score achieved by disregarding the impact of channel dynamics on data collection and device latency.  \nI. INTRODUCTION  \nThe rapid expansion of Internet of Things (IoT) devices is remarkable, with projections indicating a rise to over 29 billion devices by 2027 . Wi-Fi plays a significant role in this IoT revolution, being the backbone for 31% of IoT devices’connectivity [1] . In 2022, shipments of Wi-Fi-enabled IoT devices constituted 37% of the total market, and this figure is expected to surpass 40% by the year 2027 [2] .  \nThe growth in the number and variety of IoT devices underscores the critical need for precise device identification. Effective IoT device identification empowers network middleboxes and appliances (such as wireless Access Points (APs), switches, and network controllers) to enhance the management and security of connected devices [3], [4] . For example, to enhance security, micro-segmentation strategies can be employed to segregate devices based on their functions and security requirements [5] . Additionally, should a device exhibit unusual traffic patterns, indicative of potential security threats [6], it can be temporarily isolated for investigation. Moreover, accurate identification of IoT devices enables finetuning connectivity settings, tailored to the specific needs of each device [7] . For instance, the AP can be configured to guarantee the bandwidth of each device based on its type of service [8] . This customization not only prioritizes devices with higher importance or specific latency demands,  \nbut also significantly improves the overall user experience. Beyond operational efficiency, IoT device identification offers valuable insights into device usage, revealing patterns and behaviors instrumental in enhancing existing services or inspiring new product developments. Proactive monitoring of devices’ performance and status through identification also aids in early detection of potential malfunctions, allowing for timely interventions to prevent failures.  \nThe conventional techniques for identifying IoT devices, primarily based on IP and MAC addresses, are inadequate due to their limited applicability and susceptibility to security threats such as spoofin","cbCaimjFxx1uVJsT","https://ap.wps.com/l/cbCaimjFxx1uVJsT","pdf",1303213,1,11,"English","en",105,"# Abstract\n# Introduction\n## Motivation and role of device identification\n## Limitations of IP/MAC-based methods\n## Limitations of traffic-pattern-based approaches","[{\"question\":\"为什么需要更准确的IoT设备识别？\",\"answer\":\"准确识别用于网络监控、提升安全管控并支持设备清点，还能在设备异常或性能问题出现时进行更早的预警与隔离。\"},{\"question\":\"本文采用了什么作为设备识别的核心特征？\",\"answer\":\"使用特定探测-响应（probe-response）数据包交换的时延，称为“device latency”，作为主要特征来进行识别。\"},{\"question\":\"无线信道动态会如何影响识别效果？\",\"answer\":\"无线信道动态会降低基于层2特征的识别准确性；本文进一步提出“accumulation score”以更细粒度地刻画信道动态并提升模型训练与识别性能。\"}]","Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts | PDF",1785819664,28,{"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},"leveraging-machine-learning-for-accurate-iot-device-identification-in-dynamic-wireless-contexts","",{"@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/leveraging-machine-learning-for-accurate-iot-device-identification-in-dynamic-wireless-contexts/123988/",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","2026-08-04",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},"为什么需要更准确的IoT设备识别？","Question",{"text":75,"@type":76},"准确识别用于网络监控、提升安全管控并支持设备清点，还能在设备异常或性能问题出现时进行更早的预警与隔离。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"本文采用了什么作为设备识别的核心特征？",{"text":80,"@type":76},"使用特定探测-响应（probe-response）数据包交换的时延，称为“device latency”，作为主要特征来进行识别。",{"name":82,"@type":73,"acceptedAnswer":83},"无线信道动态会如何影响识别效果？",{"text":84,"@type":76},"无线信道动态会降低基于层2特征的识别准确性；本文进一步提出“accumulation score”以更细粒度地刻画信道动态并提升模型训练与识别性能。","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"]