[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124586-en":3,"doc-seo-124586-105":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":20,"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},124586,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",6,"Technology","Natural language based malicious domain detection using machine learning and deep learning","Cyberattacks remain a growing challenge as attackers continuously adapt their techniques to compromise targets. Malicious URLs are used to reach large audiences on social media while being disguised as legitimate web addresses, creating exposure for users and organizations and enabling subsequent attacks. Many detection systems rely on rule-based or machine learning approaches and require feature engineering, which depends on domain expertise. The proposed approach applies NLP vectorization to URL words and uses machine learning and deep learning classifiers. Experiments on two datasets show up to 92.4% and 99.5% accuracy depending on dataset and model, with Decision Tree, Random Forest, and ANN achieving strong results.","НАУЧНО-ТЕХНИЧЕСКИЙ ВЕСТНИК ИНФОРМАЦИОННЫХ ТЕХНОЛОГИЙ, МЕХАНИКИ И ОПТИКИ  \nмарт–апрель 2023 Том 23 № 2 [http://ntv.ifmo.ru/](http://ntv.ifmo.ru/)  \nSCIENTIFIC AND TECHNICAL JOURNAL OF INFORMATION TECHNOLOGIES, MECHANICS AND OPTICS  \nMarch–April 2023 Vol. 23 No 2 [http://ntv.ifmo.ru/en/](http://ntv.ifmo.ru/en/)  \n[ISSN 2226-1494](ISSN 2226-1494) ([print](print)) ISSN 2500-0373 (online)  \nмарт–апрель 2023 Том 23 Номер 2  \ndoi: 10. 17586/2226-1494-2023-23-2-304-312  \nNatural language based malicious domain detection using machine learning  \nand deep learning  \nAbdul S. Saleem Raja1􀀍 , Ganesan Pradeepa2, Somasundaram Mahalakshmi3,  \nManickam S. Jayakumar4  \n1,2,4 University of Technology and Applied Sciences, Shinas, 324, Oman  \n3 Vivekananda College of Arts and Sciences for Women, Tiruchengode, 637211, India  \n1 [asaleemrajasec@gmail.com](asaleemrajasec@gmail.com)􀀍 , [https://orcid.org/0000-0002-7203-1426](https://orcid.org/0000-0002-7203-1426)[ ](https://orcid.org/0000-0002-7203-1426)[2](2 pradeepa25.ganesan@gmail.com)[ pradeepa25.ganesan@gmail.com](2 pradeepa25.ganesan@gmail.com), [https://orcid.org/0000-0002-5920-066X](https://orcid.org/0000-0002-5920-066X)[ ](https://orcid.org/0000-0002-5920-066X)[3](3 mahalakshmimsccs@gmail.com)[ mahalakshmimsccs@gmail.com](3 mahalakshmimsccs@gmail.com), [https://orcid.org/0009-0008-5059-4384](https://orcid.org/0009-0008-5059-4384)[ ](https://orcid.org/0009-0008-5059-4384)[4](4 jaikumarmanickam@gmail.com)[ jaikumarmanickam@gmail.com](4 jaikumarmanickam@gmail.com), [https://orcid.org/0000-0002-5417-5960](https://orcid.org/0000-0002-5417-5960)  \nAbstract  \nCyberattacks are still challenging since they are increasing day by day. Cybercriminals employ a variety of strategies to manipulate and exploit their targets vulnerabilities. Malicious URLs are one such strategy which is used to target large groups on various social media platforms. To draw internet users, these web addresses are disguised as being safe. Deliberate or inadvertent use of such URLs exposes the user or the organization in the cyberspace and opens the way for further attacks. Systems that use rules-based or machine learning algorithms to find malicious URLs usually rely on feature engineering. This requires domain expertise and experience. Sometimes, even after extracting features from adataset, it may not completely leverage the potential of the dataset. The proposed method employs Natural Language Processing (NLP) approaches to vectorize the words in the URLs and applies machine learning and deep learning models for classification. Vectorization technique in NLP reduces the effort of feature engineering and maximizing the use of the dataset. For the experiment, two separate datasets are used. To vectorize the URL text, three different vectorization methods are used. To evaluate the performance of the proposed method, two different datasets (D1 and D2) that are regularly utilized in the research domain were used. The results demonstrate that the superior accuracy of 92.4 % with the D1 dataset is achieved by the Decision Tree (DT) with count vectorizer and the Random Forest (RF) with Term Frequency-Inverse Document Frequency (TF-IDF) vectorizer. With the D2 dataset, DT with TF-IDF vectorizer obtainsa greater accuracy of 99.5 %. The Artificial Neural Network (ANN) model achieves 89.6 % accuracy with the D1 dataset and 99.2 % accuracy with the D2 dataset.  \nKeywords  \nmalicious domain, phishing URL, NLP, machine learning, deep learning, ANN, CNN  \nFor citation: Saleem Raja A.S., Pradeepa G., Mahalakshmi S., Jayakumar M.S. Natural language based malicious domain detection using machine learning and deep learning. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2023, vol. 23, no. 2, pp. 304–312. doi: 10.17586/2226-1494-2023-23-2-304-312  \nУДК 004.7  \nОбнаружение вредоносного домена на основе естественного языкас использованием машинного обучения и глубокого обучения  \nАбдул Самад Салим Раджа1􀀍 , Г","cbCaimqU4acoQzhk","https://ap.wps.com/l/cbCaimqU4acoQzhk","pdf",1727471,1,9,"English","en",105,"# Abstract\n## Problem and motivation\n## Proposed NLP-based vectorization approach\n## Experimental setup and datasets\n## Results and accuracy comparison","[{\"question\":\"Why are malicious URLs considered a significant cybersecurity threat?\",\"answer\":\"Malicious URLs are disguised as safe addresses to attract users, and using them can expose individuals or organizations to attacks and enable further compromise.\"},{\"question\":\"What problem does the proposed method address compared with traditional approaches?\",\"answer\":\"Traditional systems often depend on feature engineering and domain expertise, and extracted features may not fully exploit dataset potential. The proposed method uses NLP vectorization to reduce manual feature engineering.\"},{\"question\":\"Which models and vectorizers achieved the best accuracy on each dataset?\",\"answer\":\"On dataset D1, Decision Tree with count vectorizer and Random Forest with TF-IDF achieved the highest accuracy (92.4%). On dataset D2, Decision Tree with TF-IDF vectorizer reached 99.5% accuracy, and ANN also performed strongly (99.2%).\"}]","Natural language based malicious domain detection using machine learning and deep learning | PDF",1785893178,23,{"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},"natural-language-based-malicious-domain-detection-using-machine-learning-and-deep-learning","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/natural-language-based-malicious-domain-detection-using-machine-learning-and-deep-learning/124586/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are malicious URLs considered a significant cybersecurity threat?","Question",{"text":75,"@type":76},"Malicious URLs are disguised as safe addresses to attract users, and using them can expose individuals or organizations to attacks and enable further compromise.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem does the proposed method address compared with traditional approaches?",{"text":80,"@type":76},"Traditional systems often depend on feature engineering and domain expertise, and extracted features may not fully exploit dataset potential. The proposed method uses NLP vectorization to reduce manual feature engineering.",{"name":82,"@type":73,"acceptedAnswer":83},"Which models and vectorizers achieved the best accuracy on each dataset?",{"text":84,"@type":76},"On dataset D1, Decision Tree with count vectorizer and Random Forest with TF-IDF achieved the highest accuracy (92.4%). On dataset D2, Decision Tree with TF-IDF vectorizer reached 99.5% accuracy, and ANN also performed strongly (99.2%).","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},[93,97,101,105,110,113,118,123,127,130,134],{"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":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]