[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121568-en":3,"doc-seo-121568-105":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},121568,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Effective Intrusion Detection for UAV Communications using Autoencoder-based Feature Extraction and Machine Learning Approach","This paper presents a novel intrusion detection method for unmanned aerial vehicles (UAVs) using an autoencoder-based feature extraction pipeline followed by machine learning classifiers. The approach targets realistic conditions by leveraging recent actual UAV intrusion datasets, addressing gaps where prior work relied mainly on simulated or non-UAV-relevant datasets. Experiments evaluate binary and multi-class attack classification, showing improved performance over baseline methods such as feature selection schemes.","Effective Intrusion Detection for UAV Communications using Autoencoder-based Feature Extraction and Machine Learning Approach  \nTuan-Cuong Vuong†, Cong Chi Nguyen†, Van-Cuong Pham†, Thi-Thanh-Huyen Le∗ , Xuan-Nam  \nTran∗ , and Thien Van Luong‡  \n†AIoT Lab, Faculty of Computer Science, Phenikaa University, Hanoi, Vietnam  \n∗Advanced Wireless Communications Group, Le Quy Don Technical University, Hanoi, Vietnam  \n‡Business AI Lab, Faculty of DS&AI, National Economics University, Hanoi, Vietnam  \nEmail: [thienlv@neu.edu.vn](thienlv@neu.edu.vn)  \narXiv :2410 .02827v 1 [ cs .RO] 1 Oct 2024  \nAbstract—This paper proposes a novel intrusion detection method for unmanned aerial vehicles (UAV) in the presence of recent actual UAV intrusion dataset. In particular, in the first stage of our method, we design an autoencoder architecture for effectively extracting important features, which are then fed into various machine learning models in the second stage for detecting and classifying attack types. To the best of our knowledge, this is the first attempt to propose such the autoencoder-based machine learning intrusion detection method for UAVs using actual dataset, while most of existing works only consider either simulated datasets or datasets irrelevant to UAV communications. Our experiment results show that the proposed method outperforms the baselines such as feature selection schemes in both binary and multi-class classification tasks.  \n1. Introduction  \nDrones are aircraft or submarines that are controlled remotely without a human operator, and they are often called unmanned aerial vehicles (UAVs) [4] . With their low cost, flexibility, and ease of deployment, flying technologies have been becoming increasingly attractive for unmanned missions. These vehicles can perform tasks such as surveillance, crowd control, and wireless coverage [4] . In this context, developing an intrusion detection system (IDS) to ensure safety for UAVs from attacks is really necessary.  \nTo the best of the author’s knowledge, there have been no studies, which utilizes autoencoder to improve the efficiency of IDS for UAVs in the presence of actual UAV intrusion dataset. Note that the intrusion detection systems for UAVs can use either cyber data or physical data for detecting attacks. Most of existing works in UAV intrusion detection rely either on the simulated datasets or irrelevant datasets (which are not for UAVs), while the actual datasets have been overlooked. Recently, a combination of actual cyber and physical dataset [6] has been proved to be more effective in detecting cyber attacks of UAVs than using either of them. Therefore, our current work will focus on developing a robust intrusion detection method for UAVs in the presence of the real UAV intrusion dataset [6] rather than the simulated datasets or the irrelevant datasets.  \nCorresponding author: Thien Van Luong.  \n2. Related Works  \n2.1. Related Works in Intrusion Detection for UAVs  \nAs mentioned early, most of research works in UAV intrusion detection utilize either the simulated datasets or the datasets irrelevant to UAVs. For example, in [5], an IDS for UAV that uses a hierarchical LSTM model to secure packet information was proposed, where the CICIDS-2017 dataset [11] was used for to demonstrate its ability of effectively detecting anomalies in UAV communications. Also relying on CICIDS-2017, in [1], a reinforcement Q-learning-based lightweight IDS was developed for detecting cyber attacks in UAVs. In addition,[8] combined a deep autoencoder anda convolutional neural network (CNN) for detecting malicious attacks to drones under software-defined network environments, using the virtualized InSDN dataset [2] . In the context of UAV-delivered systems, in [3], a variety of machine learning models were developed in combination with the blockchain technique for detecting attacks for reducing latency, using the CSE-CIC-IDS2018 dataset [11] .  \nAs such, all of the aforementioned research works ","cbCaidhm1mmIcY2H","https://ap.wps.com/l/cbCaidhm1mmIcY2H","pdf",196340,1,5,"English","en",105,"# Introduction\n# Related Works\n## Related Works in Intrusion Detection for UAVs\n## Autoencoder-based Intrusion Detection for UAVs","[{\"question\":\"What is the main idea of the proposed UAV intrusion detection method?\",\"answer\":\"The method first trains an autoencoder to extract important features, then feeds those features into machine learning models to detect and classify attack types.\"},{\"question\":\"Why does the paper emphasize using actual UAV intrusion datasets?\",\"answer\":\"It argues that many existing studies depend on simulated or irrelevant datasets, while realistic datasets can better reflect UAV communication attack scenarios.\"},{\"question\":\"What are the reported evaluation outcomes compared with baselines?\",\"answer\":\"Experimental results show the proposed approach outperforms baseline methods such as feature selection schemes in both binary and multi-class classification tasks.\"}]","Effective Intrusion Detection for UAV Communications using Autoencoder-based Feature Extraction and Machine Learning Approach | PDF",1785736281,13,{"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},"effective-intrusion-detection-for-uav-communications-using-autoencoder-based-feature-extraction-and-machine-learning-approach","",{"@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/effective-intrusion-detection-for-uav-communications-using-autoencoder-based-feature-extraction-and-machine-learning-approach/121568/",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 idea of the proposed UAV intrusion detection method?","Question",{"text":75,"@type":76},"The method first trains an autoencoder to extract important features, then feeds those features into machine learning models to detect and classify attack types.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why does the paper emphasize using actual UAV intrusion datasets?",{"text":80,"@type":76},"It argues that many existing studies depend on simulated or irrelevant datasets, while realistic datasets can better reflect UAV communication attack scenarios.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the reported evaluation outcomes compared with baselines?",{"text":84,"@type":76},"Experimental results show the proposed approach outperforms baseline methods such as feature selection schemes in both binary and multi-class classification tasks.","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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"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":21,"slug":137},19,"General","general"]