[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-291085-105":3,"doc-detail-291085-en":81,"detail-sidebar-cat-0-en-105":98},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","detection-of-malicious-urls-a-deep-learning-and-machine-learning-perspective","Detection of Malicious URLs: A Deep Learning and Machine Learning Perspective","","Nowadays, with rapid expansion of the cyber world, phishing and other cybersecurity threats are increasing. The paper analyzes machine learning and deep learning methods using the Crawling2024 dataset by classifying phishing versus legitimate URLs. It evaluates algorithms including Random Forest, Logistic Regression, XGBoost, MLP, GRU, and deep models such as CNN. Performance is measured with accuracy, precision, F1 score, recall, false positives, and false negatives. Results show RF achieves the highest precision (98.63%) and accuracy (96.24%), while LTRCN attains good precision but weaker accuracy (48.23%).",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/detection-of-malicious-urls-a-deep-learning-and-machine-learning-perspective/291085/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/detection-of-malicious-urls-a-deep-learning-and-machine-learning-perspective/291085.png","ImageObject",300,407,{"name":42,"@type":43},"Theodora","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-28","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the paper address?","Question",{"text":63,"@type":64},"The paper addresses detection of malicious (phishing) URLs by distinguishing them from legitimate URLs using machine learning and deep learning approaches.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which dataset and model types are used?",{"text":68,"@type":64},"It uses the Crawling2024 dataset and evaluates both machine learning algorithms (e.g., Random Forest, Logistic Regression, XGBoost, MLP, GRU) and deep learning models (e.g., CNN and other stated deep methods).",{"name":70,"@type":61,"acceptedAnswer":71},"How are the models evaluated and what is the best result?",{"text":72,"@type":64},"Models are evaluated using accuracy, precision, F1 score, recall, false positives, and false negatives. The Random Forest classifier reports the highest precision (98.63%) and accuracy (96.24%).","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},291085,1789643405,{"code":4,"msg":82,"data":83},"success",{"doc_id":79,"user_id":84,"nickname":42,"user_avatar":85,"doc_module":4,"category_id":86,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":87,"file_id":88,"file_url":89,"file_type":90,"file_size":91,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":92,"language":93,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":94,"faqs":95,"seo_title":96,"seo_description":12,"update_tm":80,"read_time":97,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"International Journal on Robotics, Automation and Sciences  \nDetection of Malicious URLs: A Deep Learning and Machine  \nLearning Perspective  \nShougfta Mushtaq* and Mazliham Mohd Su’ud  \nAbstract - Nowadays, as the cyber world is expanding rapidly, issues related to cybersecurity are also increasing. The criminal mind set try to breach the security of individual or organization by firstly, win confidence and secondly attack them for this purpose URL phishing is a most common way where phisher attach a link and share with victim. The proposed paper examines the various machine learning and deep learning approaches on state-of-the-art data set Crawling2024 by classifying the phishing and legitimate URLs. The study involves different machine learning algorithms like Random Forest, LR (Logistic Regression), XGBoost, MLP (Multilayer Perceptron) and Gated Recurrent Units (GRU) and deep learning algorithms like CNN (Convolutional Neural Network), MLP, etc. and analyze performance metrics accuracy, precision, F1 score, Recall, False Positive and False Negative. The RF (Random Forest) classifier achieved the highest precision (98.63%) and accuracy (96.24%), while Logistic Regression and GRU also achieved well. In addition to that LTRCN (Long-Term Recurrent Convolutional Network) achieved good precision but poor accuracy 48.23% . The experimental work shows that conventional algorithms such as Random Forest and advanced algorithms like GRU are efficient in detecting URL phishing, it also emphasizes that there is still need of some advanced approaches like CNN and LTRCN.  \nKeywords---Phishing URLs, URL Classification, Machine Learning, Deep Learning, Cybersecurity.  \nI. INTRODUCTION  \nPhishing is a kind of cybercrime where phisher wants to harm an individual or an organization by breaching security and successfully deceive them to reveal their confidential data such as passwords, PINs, credit card numbers or loin credentials. The common phishing attacks are usually done through fake emails, messages, or websites that seems to be trustworthy. The common strategies included modification of domain names (e.g. , \"[g00gle.com](g00gle.com)\" instead of\"[google.com](google.com)\"), modification in logo, extra subdomainsor hiding the true destination by shortening URLs. There is immense danger caused by phishing like economic loss, identity theft, financial frauds, and illegal access to accounts and making false transactions. Furthermore, breaching the security of an individual or an organization sometimes cause legal consequences and harm the reputation of organization. Phishing also includes the circulation of malware through links that effects security. A successful phishing attack can harm an organization image and break customer trust on a brand. Now, it is the need of the time to spread awareness regarding phishing, its prevention and, mitigate with attacks [1] .  \n*Corresponding author email: [shouguftawajid@yahoo.com](shouguftawajid@yahoo.com), ORCID: 0009-0000-5794-8466  \nShougfta Mushtaq : Faculty of Computing & Informatics, Multimedia University, Persiaran Multimedia, 63100 Cyberjaya, Selangor, Malaysia (e-mail: [shouguftawajid@yahoo.com](shouguftawajid@yahoo.com))  \nMazliham Mohd Su’ud: Faculty of Information Science & Technology, Multimedia University, 63100, Cyberjaya, Selangor, Malaysia (e-mail: [mazliham@mmu.edu.my](mazliham@mmu.edu.my))  \nIn cyber world several solutions related to phishing are also available like browser-based cautioning system, rule-based systems, heuristic -based methods and blacklists are also available each of them has limitations. Like in the case of blacklist used anti-phishing tool block the malicious sites but it is reactive approach and need continuous updating, which can permit new phishing techniques to attack until it is discovered. Heuristic-based approach detects the phishing by investigate the characteristics of URL, such as the length or the occurrence of the keywords, but new phishing techniques ","cbCaii1ksUvhsRWg","https://ap.wps.com/l/cbCaii1ksUvhsRWg","pdf",773015,11,"English","# I. INTRODUCTION\n## Phishing threats and common attack strategies\n## Limitations of traditional detection approaches\n## Motivation for ML and DL methods","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses detection of malicious (phishing) URLs by distinguishing them from legitimate URLs using machine learning and deep learning approaches.\"},{\"question\":\"Which dataset and model types are used?\",\"answer\":\"It uses the Crawling2024 dataset and evaluates both machine learning algorithms (e.g., Random Forest, Logistic Regression, XGBoost, MLP, GRU) and deep learning models (e.g., CNN and other stated deep methods).\"},{\"question\":\"How are the models evaluated and what is the best result?\",\"answer\":\"Models are evaluated using accuracy, precision, F1 score, recall, false positives, and false negatives. The Random Forest classifier reports the highest precision (98.63%) and accuracy (96.24%).\"}]","Detection of Malicious URLs: A Deep Learning and Machine Learning Perspective | PDF",28,{"code":4,"msg":82,"data":99},[100,104,108,112,117,122,127,130,135,138,142],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":101,"show_sort_weight":102,"slug":103},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},"Exam",70,"exam",{"id":113,"doc_module":4,"doc_module_name":25,"category_name":114,"show_sort_weight":115,"slug":116},5,"Comic",60,"comic",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},6,"Technology",50,"technology",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":125,"slug":126},7,"Healthcare",40,"healthcare",{"id":86,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":128,"slug":129},30,"research-report",{"id":131,"doc_module":4,"doc_module_name":25,"category_name":132,"show_sort_weight":133,"slug":134},9,"Religion & Spirituality",20,"religion-spirituality",{"id":133,"doc_module":4,"doc_module_name":25,"category_name":136,"show_sort_weight":133,"slug":137},"World Cup","world-cup",{"id":139,"doc_module":4,"doc_module_name":25,"category_name":140,"show_sort_weight":139,"slug":141},10,"Lifestyle","lifestyle",{"id":143,"doc_module":4,"doc_module_name":25,"category_name":144,"show_sort_weight":113,"slug":145},19,"General","general"]