{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/53423"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/53423","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Using Large Language Models to predict unknown domain names","abstract":"Many organizations maintain internal domain names and URLs that are private and not publicly accessible. This thesis explores the challenge of predicting such unknown or private URLs using modern Large Language Models and Deep Learning techniques. The task is particularly difficult due to the lack of visibility into the types and structures of URLs stored in local DNS servers. While Large Language Models (LLMs) have shown impressive capabilities across various domains, they are prone to hallucination and may struggle with generating realistic, previously unseen URLs. In this work, we investigate the use of LLMs—either through training from scratch or fine-tuning pre-trained models—to generate and predict valid domain names. Our approach leverages a large corpus of existing global and organizational DNS data to guide the model toward plausible and contextually appropriate URL predictions.","abstract_html":"Many organizations maintain internal domain names and URLs that are private and not publicly accessible. This thesis explores the challenge of predicting such unknown or private URLs using modern Large Language Models and Deep Learning techniques. The task is particularly difficult due to the lack of visibility into the types and structures of URLs stored in local DNS servers. While Large Language Models (LLMs) have shown impressive capabilities across various domains, they are prone to hallucination and may struggle with generating realistic, previously unseen URLs. In this work, we investigate the use of LLMs—either through training from scratch or fine-tuning pre-trained models—to generate and predict valid domain names. Our approach leverages a large corpus of existing global and organizational DNS data to guide the model toward plausible and contextually appropriate URL predictions.","abstract_has_math":false,"creators":["Sharma, Ayush"],"institution":"Boston University","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Crovella, Mark"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-18T19:48:01Z","subjects":["Artificial intelligence"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2144/53423","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/53423","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F53423","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Crovella, Mark"]},{"key":"dc:creator","label":"Author","values":["Sharma, Ayush"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-07-31T17:23:07Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-07-31T17:23:07Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2026-07-22T22:15:33Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/53423"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["2025"]},{"key":"dc:description.abstract","label":"Abstract","values":["Many organizations maintain internal domain names and URLs that are private and not publicly accessible. This thesis explores the challenge of predicting such unknown or private URLs using modern Large Language Models and Deep Learning techniques. The task is particularly difficult due to the lack of visibility into the types and structures of URLs stored in local DNS servers. While Large Language Models (LLMs) have shown impressive capabilities across various domains, they are prone to hallucination and may struggle with generating realistic, previously unseen URLs. In this work, we investigate the use of LLMs—either through training from scratch or fine-tuning pre-trained models—to generate and predict valid domain names. Our approach leverages a large corpus of existing global and organizational DNS data to guide the model toward plausible and contextually appropriate URL predictions."]},{"key":"dc:title","label":"Title","values":["Using Large Language Models to predict unknown domain names"]}]}],"canonical_facts":{"dc:contributor.advisor":["Crovella, Mark"],"dc:creator":["Sharma, Ayush"],"dc:date.accessioned":["2026-07-31T17:23:07Z"],"dc:date.available":["2026-07-31T17:23:07Z"],"dc:date.issued":["2025"],"dc:date.updated":["2026-07-22T22:15:33Z"],"dc:description":["2025"],"dc:description.abstract":["Many organizations maintain internal domain names and URLs that are private and not publicly accessible. This thesis explores the challenge of predicting such unknown or private URLs using modern Large Language Models and Deep Learning techniques. The task is particularly difficult due to the lack of visibility into the types and structures of URLs stored in local DNS servers. While Large Language Models (LLMs) have shown impressive capabilities across various domains, they are prone to hallucination and may struggle with generating realistic, previously unseen URLs. In this work, we investigate the use of LLMs—either through training from scratch or fine-tuning pre-trained models—to generate and predict valid domain names. Our approach leverages a large corpus of existing global and organizational DNS data to guide the model toward plausible and contextually appropriate URL predictions."],"dc:identifier.uri":["https://hdl.handle.net/2144/53423"],"dc:language.iso":["en_US"],"dc:subject":["Artificial intelligence"],"dc:title":["Using Large Language Models to predict unknown domain names"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T19:48:01Z"}