{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308338440"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308338440","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Didžiųjų kalbos modelių ir specializuotų neuroninių tinklų taikymas URL phishing atpažinimui /","abstract":"This bachelor’s thesis investigates the problem of phishing and its detection using modern machine learning algorithms. Since traditional security methods, such as blacklisting, o&#383;ten fail to identify newly created threats in realtime, the study focuses on the effectiveness of specialized neural networks and ensemble tree algorithms in identifying malicious URLs. The experimental study was conducted using the “PhiUSIIL” dataset, which, a&#383;ter pre processing, consisted of over 150000 unique records. Two models were implemented and compared: a MultiLayer Perceptron (MLP) and the “XGBoost” algorithm. The research results demonstrated that the “XGBoost” model achieved an exceptionally high classification accuracy of 96.28%. To ensure decision transparency, the LIME method was applied to interpret the “black box” decisions made by the models and to identify critical URL features. The findings of the study confirm that machine learning, combined with explainable AI tools, provides a reliable and transparent solution for combating phishing websites.","abstract_html":"This bachelor’s thesis investigates the problem of phishing and its detection using modern machine learning algorithms. Since traditional security methods, such as blacklisting, o&amp;#383;ten fail to identify newly created threats in realtime, the study focuses on the effectiveness of specialized neural networks and ensemble tree algorithms in identifying malicious URLs. The experimental study was conducted using the “PhiUSIIL” dataset, which, a&amp;#383;ter pre processing, consisted of over 150000 unique records. Two models were implemented and compared: a MultiLayer Perceptron (MLP) and the “XGBoost” algorithm. The research results demonstrated that the “XGBoost” model achieved an exceptionally high classification accuracy of 96.28%. To ensure decision transparency, the LIME method was applied to interpret the “black box” decisions made by the models and to identify critical URL features. The findings of the study confirm that machine learning, combined with explainable AI tools, provides a reliable and transparent solution for combating phishing websites.","abstract_has_math":false,"creators":["Pliuskus, Povilas,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:59Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308338440&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308338440&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308338440","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Pliuskus, Povilas,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308338440/308338440.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308338440&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This bachelor’s thesis investigates the problem of phishing and its detection using modern machine learning algorithms. Since traditional security methods, such as blacklisting, o&#383;ten fail to identify newly created threats in realtime, the study focuses on the effectiveness of specialized neural networks and ensemble tree algorithms in identifying malicious URLs. The experimental study was conducted using the “PhiUSIIL” dataset, which, a&#383;ter pre processing, consisted of over 150000 unique records. Two models were implemented and compared: a MultiLayer Perceptron (MLP) and the “XGBoost” algorithm. The research results demonstrated that the “XGBoost” model achieved an exceptionally high classification accuracy of 96.28%. To ensure decision transparency, the LIME method was applied to interpret the “black box” decisions made by the models and to identify critical URL features. The findings of the study confirm that machine learning, combined with explainable AI tools, provides a reliable and transparent solution for combating phishing websites."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Didžiųjų kalbos modelių ir specializuotų neuroninių tinklų taikymas URL phishing atpažinimui /","Application of large language models and specialised neural networks for phishing url detection."]}]}],"canonical_facts":{"dc:creator":["Pliuskus, Povilas,"],"dc:date":["2026"],"dc:description":["This bachelor’s thesis investigates the problem of phishing and its detection using modern machine learning algorithms. Since traditional security methods, such as blacklisting, o&#383;ten fail to identify newly created threats in realtime, the study focuses on the effectiveness of specialized neural networks and ensemble tree algorithms in identifying malicious URLs. The experimental study was conducted using the “PhiUSIIL” dataset, which, a&#383;ter pre processing, consisted of over 150000 unique records. Two models were implemented and compared: a MultiLayer Perceptron (MLP) and the “XGBoost” algorithm. The research results demonstrated that the “XGBoost” model achieved an exceptionally high classification accuracy of 96.28%. To ensure decision transparency, the LIME method was applied to interpret the “black box” decisions made by the models and to identify critical URL features. The findings of the study confirm that machine learning, combined with explainable AI tools, provides a reliable and transparent solution for combating phishing websites."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308338440&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308338440/308338440.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Didžiųjų kalbos modelių ir specializuotų neuroninių tinklų taikymas URL phishing atpažinimui /","Application of large language models and specialised neural networks for phishing url detection."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:59Z"}