[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119414-id":3,"doc-seo-119414-113":31,"detail-sidebar-cat-0-id-113":92},{"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},119414,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",52,"Teknologi","Deteksi Website Phishing Menggunakan Teknik Machine Learning - Abstrak dan Implementasi","Phishing merupakan teknik penipuan yang menyamar sebagai entitas tepercaya untuk mencuri data sensitif melalui media elektronik seperti email dan situs web palsu. Penelitian ini menguji metode supervised learning berbasis machine learning, yaitu XGBoost, Random Forest, dan Decision Tree, untuk mengenali pola pada halaman dan URL. Hasil komparasi menunjukkan XGBoost dengan hyperparameter tuning mencapai akurasi 96%. Model kemudian diimplementasikan sebagai web service real-time menggunakan Flask/FastAPI, dilengkapi ekstraksi fitur (analisis URL, umur domain, konten halaman) serta pelabelan otomatis. Integrasi Telegram bot meningkatkan aksesibilitas, sehingga pengguna dapat melakukan deteksi kapan saja lewat pesan instan.","Deteksi Website Phishing Menggunakan Teknik Machine Learning  \nLukito, Wilfridus Bambang Triadi Handaya2  \nProgram Studi Informatika, Fakultas Teknologi Industri, Universitas Atma Jaya Yogyakarta Jl. Babarsari No.44, 55281, Daerah Istimewa Yogyakarta, Indonesia [Email:](Email:1200710677@students.uajy.ac.id)[1](Email:1200710677@students.uajy.ac.id)[200710677@students.uajy.ac.id](Email:1200710677@students.uajy.ac.id), [2](2wilfridus.handaya@uajy.ac.id)[wilfridus.handaya@uajy.ac.id](2wilfridus.handaya@uajy.ac.id)  \nAbstract. Phishing is a fraudulent technique that involves masquerading as a trusted entity to steal sensitive data. Machine learning-based detection methods, including XGBoost, Random Forest, and Decision Tree, have been demonstrated to be effective in recognizing patterns indicative of phishing websites. The findings indicate that XGBoost with hyperparameter tuning attains the highest level of accuracy, reaching 96%. After this analysis, the model is implemented in a web service using Flask or FastAPI, enabling users to verify URLs in real time. The system is further equipped with a feature extraction mechanism, encompassing URL analysis, domain age, page content, and automatic labeling to facilitate model retraining. Furthermore, the integration of the system with Telegram bots serves to enhance accessibility, thereby enabling users to perform phishing detection at any time via instant messaging without the constraints of location or device restrictions.  \nKeywords: Machine Learning, Supervised Learning, Phishing  \nAbstrak. Phishing merupakan teknik penipuanyang memanfaatkanpenyamaran sebagai entitas terpercaya untuk mencuri data sensitif. Metode deteksi berbasis machine learning, seperti XGBoost, Random Forest, dan Decision Tree, efektif dalam mengenali pola website phishing. Hasil penelitian menunjukkan bahwaXGBoost dengan hyperparameter tuning memberikan akurasi tertinggi, yaitu 96%. Model ini kemudian diimplementasikandalam web service menggunakan Flask atau FastAPI, sehingga pengguna dapat memeriksa URL secara real-time. Sistem juga dilengkapi mekanisme ekstraksi fitur, termasukanalisis URL, domain age, dan konten halaman, sertapelabelan otomatis untukmemudahkan pelatihan ulang model. Selain itu, integrasi dengan bot Telegram memperluasaksesibilitas, karena pengguna dapat melakukan deteksi phishing kapan sajamelalui pesan instan tanpa batasan lokasi atauperangkat.  \nKata Kunci: Machine Learning, Supervised Learning, Phishing  \n1. Pendahuluan  \nPhishing merupakan teknik penipuan yang berupaya memperoleh informasi sensitif, seperti nama pengguna, kata sandi, dan detail kartu kredit, dengan menyamar sebagai entitasterpercaya melalui komunikasi elektronik [1] . Perkembangan teknologi yang pesat menyebabkan ancaman ini terus meningkat, terutama melalui email dan situs web palsu. Berdasarkan laporan Cloudflare pada tahun 2023, sebanyak 90% serangan cyber yang berhasil dilakukan memanfaatkan email sebagai sarana utama. Dalam kurun waktu Mei 2022 hingga Mei 2023, Cloudflare memproses sekitar 13 juta email serta memblokir 250 juta pesan berbahaya sebelum mencapai pengguna [2] . Mengingat kerugian yang ditimbulkan oleh serangan phishing kian signifikan, berbagai upaya mitigasi perlu dilakukan. Salah satu pendekatan yang banyak mendapatkan perhatian adalah penerapan sistem deteksi phishing menggunakan machine learning (ML), khususnya metode supervised learning seperti XGBoost, Decision Tree, dan Random Forest dikarenakan kemampuannya dalam menangani data yang kompleks, memberikan hasil yang akurat serta mendukung optimasi model dalam berbagai jenis dataset. Model-model ini memanfaatkan dataset berlabel untuk mengidentifikasi pola-pola yang membedakan situs web phishing dari situs web yang sah [3]–[14] .  \nPemilihan algoritma XGBoost, Decision Tree, dan Random Forest dalam sistem deteksi phishing didasarkan pada bukti empiris yang menunjukkan akurasi tinggi dan kemampuan adaptasi terhadap data yang kompleks. Random Forest ","cbCaicyW3QkKiuwq","https://ap.wps.com/l/cbCaicyW3QkKiuwq","pdf",757207,2,1,12,"Indonesian","id",113,"# Pendahuluan\n## Latar belakang ancaman phishing\n## Pendekatan deteksi berbasis machine learning\n## Pembandingan algoritma XGBoost, Decision Tree, dan Random Forest\n# Tujuan penelitian\n## Evaluasi berbasis akurasi, presisi, recall, dan F1-score","[{\"question\":\"Apa tujuan utama penelitian deteksi website phishing ini?\",\"answer\":\"Tujuan penelitian adalah membandingkan tiga algoritma machine learning (XGBoost, Decision Tree, dan Random Forest) untuk memilih model yang paling sesuai diterapkan sebagai sistem deteksi phishing.\"},{\"question\":\"Algoritma mana yang memperoleh akurasi tertinggi, dan berapa nilainya?\",\"answer\":\"XGBoost dengan hyperparameter tuning memperoleh akurasi tertinggi, yaitu 96%.\"},{\"question\":\"Bagaimana sistem deteksi diimplementasikan dan fitur apa yang diekstraksi?\",\"answer\":\"Model diimplementasikan dalam web service real-time menggunakan Flask atau FastAPI. Sistem mengekstraksi fitur seperti analisis URL, umur domain, konten halaman, serta melakukan pelabelan otomatis untuk membantu pelatihan ulang model.\"}]","Deteksi Website Phishing Menggunakan Teknik Machine Learning - Abstrak dan Implementasi | PDF",1785724168,18,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"phishing-website-detection-using-machine-learning-techniques-abstract-and-implementation","",{"@graph":37,"@context":86},[38,54,69],{"@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/id/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/id/document/teknologi/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/id/document/phishing-website-detection-using-machine-learning-techniques-abstract-and-implementation/119414/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-15","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Apa tujuan utama penelitian deteksi website phishing ini?","Question",{"text":76,"@type":77},"Tujuan penelitian adalah membandingkan tiga algoritma machine learning (XGBoost, Decision Tree, dan Random Forest) untuk memilih model yang paling sesuai diterapkan sebagai sistem deteksi phishing.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Algoritma mana yang memperoleh akurasi tertinggi, dan berapa nilainya?",{"text":81,"@type":77},"XGBoost dengan hyperparameter tuning memperoleh akurasi tertinggi, yaitu 96%.",{"name":83,"@type":74,"acceptedAnswer":84},"Bagaimana sistem deteksi diimplementasikan dan fitur apa yang diekstraksi?",{"text":85,"@type":77},"Model diimplementasikan dalam web service real-time menggunakan Flask atau FastAPI. Sistem mengekstraksi fitur seperti analisis URL, umur domain, konten halaman, serta melakukan pelabelan otomatis untuk membantu pelatihan ulang model.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,99,103,107,111,115,119,123,125,129,133],{"id":95,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},55,"Agama & Spiritualitas",60,"religion-spirituality",{"id":100,"doc_module":4,"doc_module_name":47,"category_name":101,"show_sort_weight":97,"slug":102},48,"Cerita & Novel","story-novel",{"id":104,"doc_module":4,"doc_module_name":47,"category_name":105,"show_sort_weight":97,"slug":106},56,"Gaya Hidup","lifestyle",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":97,"slug":110},51,"Komik","comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":97,"slug":114},53,"Layanan Kesehatan","healthcare",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":97,"slug":118},54,"Penelitian & Laporan","research-report",{"id":120,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":97,"slug":122},49,"Sastra","literature",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":97,"slug":124},"technology",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":127,"show_sort_weight":97,"slug":128},50,"Ujian","exam",{"id":130,"doc_module":4,"doc_module_name":47,"category_name":131,"show_sort_weight":97,"slug":132},57,"Umum","general",{"id":134,"doc_module":4,"doc_module_name":47,"category_name":135,"show_sort_weight":4,"slug":136},181,"Formulir","formulir"]