[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121609-en":3,"doc-seo-121609-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},121609,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Optimising Phishing Detection - A Comparative Analysis of Machine Learning Methods with Feature Selection","Phishing is a cybersecurity attack that manipulates users into disclosing sensitive information. Because existing defenses remain inefficient, machine learning has become a key approach for phishing detection. This study investigates how machine learning models combined with feature selection techniques perform in identifying and classifying phishing sites, using Random Forest and Artificial Neural Network together with PCA and RFE. Experiments on 4,898 phishing and 6,157 legitimate sites show RF with PCA reaches 95.83% accuracy and ANN with PCA reaches 95.07%, improving computational efficiency and reducing overfitting.","Journal of Informatics and Web Engineering  \nVol. 4 No. 1(February 2025) eISSN: 2821-370  \nOptimising Phishing Detection: A Comparative Analysis of Machine Learning Methods with  \nFeature Selection  \nMohamad Asraf Daniel1, Siew-Chin Chong2*, Lee-Ying Chong3, Kuok-Kwee Wee4  \n1,2,3,4 Faculty of Information Science & Technology, Multimedia University, Jalan Ayer Keroh Lama, 75450 Melaka, Malaysia  \n*corresponding author: ([chong.siew.chin@mmu.edu.my](chong.siew.chin@mmu.edu.my); ORCiD: 0000-0003-0421-4367)  \nAbstract-Phishing is an act of cybersecurity attack that tricks people into sharing sensitive data. Due to the inefficiency of the current security technologies, researchers have been paying much attention to employing machine learning methods for phishing detection lately. In our proposed solution, the effectiveness of machine learning techniques with feature selection techniques for phishing detection is investigated. To be specific, Random Forest (RF) and Artificial Neural Network (ANN) are integrated with feature selection techniques, Principal Component Analysis (PCA) and Recursive Feature Elimination (RFE) . The goal was to identify and classify the model with the highest accuracy. The experiments were evaluated using a dataset of 4,898 phishing sites and 6,157 legitimate sites, [with the phishing data sourced from Kaggle.com. Our experiments demonstrate that](with the phishing data sourced from Kaggle.com. Our experiments demonstrate that) the combination of RF model with PCA achieved 95.83% accuracy, while the ANN model with PCA reached 95.07% accuracy. The incorporation of PCA and RFE not only optimised the models' predictive performance but also improved computational efficiency. Overfitting can also be reduced. The experimental results also demonstrate that the proposed ANN with PCA method outperforms the state-of-theart methods. Consequently, this research highlights the potential of combining advanced feature selection techniques with machine learning algorithms to develop robust solutions for phishing detection. Yet, this undoubtedly contributes to a safer internet environment.  \nKeywords—Machine Learning, Phishing Detection, Feature Selection, Dimension Reduction, Cyber-attacks.  \nReceived: 15 August 2024; Accepted: 24 December 2024; Published: 16 February 2025  \nThis is an open access article under the CC BY-NC-ND 4.0 license.  \n1. INTRODUCTION  \nIn recent years, the growth of electronic trading has led to a significant increase in cyber-attacks. Many strategies have been prompted to overcome these challenges [1],[2],[3]. Among the challenges, phishing attacks are serious concerns for individuals and organizations. These attacks cause the loss of sensitive data such as user credentials and finance information. Phishing attacks often involve the use of fraudulent websites which are hard to detect by the users easily. Therefore, detecting phishing websites has become a crucial task for cybersecurity professionals.  \nOne way to address the issue is by using machine learning (ML) techniques. ML algorithms can be trained to automatically identify phishing websites through analyzing various features of the website, such as the domain name, content, and layout. However, ML models [4], [5], [6] may struggle to generalize across new, unseen phishing tactics that differ significantly from the training data. This often leads to potential false negatives. Our research work aims to investigate the use of ML for detecting phishing websites and to propose an optimal model to overcome the weaknesses. The proposed work includes collecting a dataset of websites, extracting features, developing ML algorithms, and evaluating the performance of the model. The expected outcome is an automated approach for detecting phishing websites with higher accuracy.  \nThis research introduces the implementation of machine learning techniques, specifically RF and ANN algorithms, tobe combined with PCA and RFE. RF is chosen due to its robustnes","cbCaiiYtHxpT83vN","https://ap.wps.com/l/cbCaiiYtHxpT83vN","pdf",714767,2,1,13,"English","en",105,"# Introduction\n## Machine learning for phishing detection\n## Proposed approach\n# Literature Review\n## Prior ML methods for phishing detection\n## Comparative evaluations and results","[{\"question\":\"What problem does this research address in phishing detection?\",\"answer\":\"It targets the difficulty of detecting phishing websites and the limitations of current security technologies and ML models when facing new, unseen phishing tactics.\"},{\"question\":\"Which machine learning models and feature selection methods are used?\",\"answer\":\"The study integrates Random Forest (RF) and Artificial Neural Network (ANN) with PCA and Recursive Feature Elimination (RFE) for feature selection and dimensionality reduction.\"},{\"question\":\"What datasets and performance results are reported?\",\"answer\":\"Experiments use 4,898 phishing sites and 6,157 legitimate sites; RF with PCA achieves 95.83% accuracy and ANN with PCA reaches 95.07% accuracy.\"}]","Optimising Phishing Detection - A Comparative Analysis of Machine Learning Methods with Feature Selection | PDF",1785736466,33,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":29},"optimising-phishing-detection-a-comparative-analysis-of-machine-learning-methods-with-feature-selection","",{"@graph":37,"@context":85},[38,54,68],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/optimising-phishing-detection-a-comparative-analysis-of-machine-learning-methods-with-feature-selection/121609/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",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},"What problem does this research address in phishing detection?","Question",{"text":75,"@type":76},"It targets the difficulty of detecting phishing websites and the limitations of current security technologies and ML models when facing new, unseen phishing tactics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models and feature selection methods are used?",{"text":80,"@type":76},"The study integrates Random Forest (RF) and Artificial Neural Network (ANN) with PCA and Recursive Feature Elimination (RFE) for feature selection and dimensionality reduction.",{"name":82,"@type":73,"acceptedAnswer":83},"What datasets and performance results are reported?",{"text":84,"@type":76},"Experiments use 4,898 phishing sites and 6,157 legitimate sites; RF with PCA achieves 95.83% accuracy and ANN with PCA reaches 95.07% accuracy.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]