[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120481-id":3,"doc-seo-120481-113":31,"detail-sidebar-cat-0-id-113":93},{"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},120481,962085570644,"Evangeline","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",54,"Penelitian & Laporan","Deteksi Serangan Web Defacement pada Infrastruktur Kritis Menggunakan Machine Learning","Ancaman terhadap keamanan situs web dan server meningkat setiap tahun, terutama pada kasus Web Defacement yang dapat mengubah tampilan atau isi halaman secara tidak sah. Dampaknya menjadi lebih serius ketika target termasuk infrastruktur kritis seperti pemerintahan, kesehatan, dan energi karena dapat memicu gangguan layanan vital, kerugian ekonomi, serta penurunan kepercayaan publik. Penelitian ini menerapkan supervised machine learning untuk mendeteksi defacement secara adaptif, menggunakan dataset web defacement publik dan situs simulasi. Tiga model, yaitu Random Forest, SVM, dan Naive Bayes, dievaluasi dengan hasil bahwa Random Forest mencapai akurasi hingga 96% untuk identifikasi website yang telah di-deface, sehingga mendukung pengembangan deteksi dini berbasis ML untuk perlindungan infrastruktur penting.","Deteksi Serangan Web Defacement pada Infrastruktur Kritis Menggunakan Machine learning  \n(The Detection of Web Defacement Attacks on Critical Infrastructure Using Machine Learning)  \nVictor Eric Pattiradjawane1*, Doms Upuy1  \n1Program Studi Ilmu Komputer, Fakultas Sains dan Teknologi, Universitas Pattimura Jl. Ir. M. Putuhena, Ambon, 97233, Indonesia  \n* Corresponding author’s e-mail: * [victor.pattiradjawane@lecturer.unpatti.ac.id](victor.pattiradjawane@lecturer.unpatti.ac.id)  \n\n| Manuscript submitted: February 2025 | Manuscript revision: March 2025 | Accepted for publication: May 2025 |\n| --- | --- | --- |\n| Abstract\u003Cbr>The number of threats to the security of websites and web servers, which include things like Web Defacement, is increasing every year. This is a major concern in today's cybersecurity world. It includes websites that are part of critical infrastructure, like government, health, and energy systems. This research study looks at how machine learning (ML) models can automatically detect Web Defacement attacks. The main goal is to make sure these models are very accurate. We developed a supervised learning-based classification model using Web Defacement datasets from public archives and simulated mock sites. This research study looks at how well three types of classification models—Random Forest, support vector machine (SVM), and naive Bayes—perform at identifying defaced websites. The results of the experiment show that Random Forest is the best option, with up to 96% accuracy. This research shows that the Machine learning (ML) approach could be very important in developing a system that can detect cyberattacks early on. This system would protect important infrastructure in the country.\u003Cbr>Keywords: Anomaly Detection, Critical Infrastructure, Cybersecurity, Machine learning, Web Defacement. |  |  |\n\nThis article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-ShareAlike 4.0 International License.  \n1. PENDAHULUAN  \n1.1. Latar Belakang  \nDalam beberapa tahun terakhir, insiden keamanan siber mengalami peningkatan signifikan, baik dari segi frekuensi, kompleksitas, maupun target serangan. Salah satu bentuk serangan yangumum namun berdampak besar adalah Web Defacement [1] . Seranganinimengubah tampilanatau isi halaman web dengan konten yang tidak sah, sering kali bersifat provokatif atau merusak citra  \norganisasi. Ketika situs yang diserang termasuk dalam infrastruktur kritis seperti pemerintahan, kesehatan, dan energi, konsekuensinya mencakup gangguan layanan vital, kerugian ekonomi, serta penurunan kepercayaan publik.  \nDeteksi serangan Web Defacement secara manual atau berbasis signature sering kali tidak mampu mengimbangi kecepatan dan variasi serangan. Untuk itu, pendekatan machine learning (ML) muncul sebagai solusi yang adaptif dan cerdas. Model ML dapat dilatih untuk mengenali anomali pada konten halaman web berdasarkan pola-pola historis, sehingga mampu mendeteksi serangan yang sebelumnya belum dikenal (zero-day attack) .  \nPenelitian ini bertujuan menerapkan dan mengevaluasi performa beberapa model atau algoritma ML dalam mendeteksi halaman web yang telah di-deface. Hasil dari penelitian inidiharapkan dapat mendukung pengembangan sistem deteksi dini berbasis ML yang efisien danakurat untuk perlindungan infrastruktur kritis di Indonesia.  \n2. TINJAUAN PUSTAKA  \nBerbagai penelitian telah dilakukan terkait deteksi serangan Web Defacement. Metode berbasis signature tidak mampu mendeteksi serangan baru secara efektif [2] . Pendekatan visual berbasis CNN telah digunakanuntuk mendeteksi perubahantampilan halaman web [3], sedangkan perbandinganalgoritmaklasifikasi menunjukkan efektivitas yang beragam dalam mendeteksi webberbahaya [4] .  \nMetode deteksi anomali relevan untuk diterapkan dalam konteks defacement [5], [6] . Ekstraksi fitur HTML juga dianggap penting dalam membedakan konten sah dankontenyangtelah diubah [7] . Pendekatan hybrid yang menggabungkan","cbCaikJuQRigwPjy","https://ap.wps.com/l/cbCaikJuQRigwPjy","pdf",398087,6,1,5,"Indonesian","id",113,"# PENDAHULUAN\n## Latar Belakang\n# TINJAUAN PUSTAKA\n# METODE PENELITIAN\n## Akuisisi dan Klasifikasi Dataset\n## Pra-Pemrosesan Data","[{\"question\":\"Apa tujuan penelitian deteksi Web Defacement pada infrastruktur kritis?\",\"answer\":\"Penelitian bertujuan menerapkan dan mengevaluasi performa beberapa model machine learning untuk mendeteksi halaman web yang telah di-deface guna mendukung pengembangan sistem deteksi dini yang efisien dan akurat.\"},{\"question\":\"Dataset apa yang digunakan untuk membangun model deteksi?\",\"answer\":\"Dataset terdiri dari halaman web normal dan halaman web defacement, bersumber dari arsip zone-h untuk data publik serta simulasi defacement lokal, dengan total 100 sampel dan distribusi seimbang antar kelas.\"},{\"question\":\"Model klasifikasi apa yang menghasilkan performa terbaik dan berapa akurasinya?\",\"answer\":\"Random Forest menunjukkan performa terbaik dengan akurasi hingga 96% dalam mengidentifikasi website yang telah mengalami defacement.\"}]","Deteksi Serangan Web Defacement pada Infrastruktur Kritis Menggunakan Machine Learning | PDF",1785730302,8,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"detecting-web-defacement-attacks-on-critical-infrastructure-using-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/id/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/id/document/penelitian-laporan/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/id/document/detecting-web-defacement-attacks-on-critical-infrastructure-using-machine-learning/120481/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-18","2026-08-03",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Apa tujuan penelitian deteksi Web Defacement pada infrastruktur kritis?","Question",{"text":77,"@type":78},"Penelitian bertujuan menerapkan dan mengevaluasi performa beberapa model machine learning untuk mendeteksi halaman web yang telah di-deface guna mendukung pengembangan sistem deteksi dini yang efisien dan akurat.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Dataset apa yang digunakan untuk membangun model deteksi?",{"text":82,"@type":78},"Dataset terdiri dari halaman web normal dan halaman web defacement, bersumber dari arsip zone-h untuk data publik serta simulasi defacement lokal, dengan total 100 sampel dan distribusi seimbang antar kelas.",{"name":84,"@type":75,"acceptedAnswer":85},"Model klasifikasi apa yang menghasilkan performa terbaik dan berapa akurasinya?",{"text":86,"@type":78},"Random Forest menunjukkan performa terbaik dengan akurasi hingga 96% dalam mengidentifikasi website yang telah mengalami defacement.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,100,104,108,112,116,118,122,126,130,134],{"id":96,"doc_module":4,"doc_module_name":47,"category_name":97,"show_sort_weight":98,"slug":99},55,"Agama & Spiritualitas",60,"religion-spirituality",{"id":101,"doc_module":4,"doc_module_name":47,"category_name":102,"show_sort_weight":98,"slug":103},48,"Cerita & Novel","story-novel",{"id":105,"doc_module":4,"doc_module_name":47,"category_name":106,"show_sort_weight":98,"slug":107},56,"Gaya Hidup","lifestyle",{"id":109,"doc_module":4,"doc_module_name":47,"category_name":110,"show_sort_weight":98,"slug":111},51,"Komik","comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":98,"slug":115},53,"Layanan Kesehatan","healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":98,"slug":117},"research-report",{"id":119,"doc_module":4,"doc_module_name":47,"category_name":120,"show_sort_weight":98,"slug":121},49,"Sastra","literature",{"id":123,"doc_module":4,"doc_module_name":47,"category_name":124,"show_sort_weight":98,"slug":125},52,"Teknologi","technology",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":128,"show_sort_weight":98,"slug":129},50,"Ujian","exam",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":132,"show_sort_weight":98,"slug":133},57,"Umum","general",{"id":135,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":4,"slug":137},181,"Formulir","formulir"]