{"id":"https://openalex.org/W4399852625","doi":"https://doi.org/10.23919/tma62044.2024.10559115","title":"More than Words is What you Need - Detecting DGA and Phishing Domains with Dom2Vec Word Embeddings","display_name":"More than Words is What you Need - Detecting DGA and Phishing Domains with Dom2Vec Word Embeddings","publication_year":2024,"publication_date":"2024-05-21","ids":{"openalex":"https://openalex.org/W4399852625","doi":"https://doi.org/10.23919/tma62044.2024.10559115"},"language":"en","primary_location":{"id":"doi:10.23919/tma62044.2024.10559115","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/tma62044.2024.10559115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 8th Network Traffic Measurement and Analysis Conference (TMA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030894737","display_name":"Lucas Torrealba Aravena","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Lucas Torrealba Aravena","raw_affiliation_strings":["Universidad de Chile,NIC Labs","NIC Labs, Universidad de Chile"],"affiliations":[{"raw_affiliation_string":"Universidad de Chile,NIC Labs","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"NIC Labs, Universidad de Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081556750","display_name":"Pedro Casas","orcid":"https://orcid.org/0000-0002-0951-2331"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Pedro Casas","raw_affiliation_strings":["AIT Austrian Institute of Technology"],"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062341453","display_name":"Javier Bustos-Jim\u00e9nez","orcid":"https://orcid.org/0000-0003-0036-2004"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Javier Bustos-Jim\u00e9nez","raw_affiliation_strings":["Universidad de Chile,NIC Labs","NIC Labs, Universidad de Chile"],"affiliations":[{"raw_affiliation_string":"Universidad de Chile,NIC Labs","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"NIC Labs, Universidad de Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039503631","display_name":"Mislav Findrik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mislav Findrik","raw_affiliation_strings":["cyan Security Group"],"affiliations":[{"raw_affiliation_string":"cyan Security Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030894737"],"corresponding_institution_ids":["https://openalex.org/I69737025"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12159603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9013000130653381,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9010000228881836,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.7905712127685547},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7617150545120239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6779958009719849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6240344643592834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5154593586921692},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23803383111953735},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.20195135474205017},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1882529854774475}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.7905712127685547},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7617150545120239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779958009719849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6240344643592834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5154593586921692},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23803383111953735},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.20195135474205017},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1882529854774475},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/tma62044.2024.10559115","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/tma62044.2024.10559115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 8th Network Traffic Measurement and Analysis Conference (TMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2040750298","https://openalex.org/W2136495567","https://openalex.org/W2913504480","https://openalex.org/W2914448461","https://openalex.org/W2972765591","https://openalex.org/W2972832672","https://openalex.org/W3097435565","https://openalex.org/W3114681532","https://openalex.org/W3175769352","https://openalex.org/W3200507345","https://openalex.org/W4294170691","https://openalex.org/W4384158012","https://openalex.org/W4389077640","https://openalex.org/W6636510571","https://openalex.org/W6682691769"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2149202530","https://openalex.org/W2807822918","https://openalex.org/W2921723332","https://openalex.org/W2482950156","https://openalex.org/W2305322260","https://openalex.org/W3139248031","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"The":[0],"rapid":[1],"detection":[2,46,135],"of":[3,47,80,106,114,125,136],"Domain":[4,66],"Generation":[5],"Algorithm":[6],"(DGA)":[7],"and":[8,20,34,49,89,117],"general":[9,118],"phishing":[10,50,119,129],"domains":[11,116],"plays":[12],"a":[13,40,73,103],"critical":[14],"role":[15],"in":[16,27,60,131],"mitigating":[17],"malware":[18],"propagation":[19],"its":[21],"potential":[22],"impact,":[23],"as":[24,26],"well":[25],"limiting":[28],"botnet":[29],"activity":[30],"coordination":[31],"through":[32],"command":[33],"control":[35],"(C&C)":[36],"servers.":[37],"We":[38],"assess":[39],"learning":[41],"driven":[42],"approach":[43],"for":[44,128,133],"accurate":[45],"DGA-generated":[48],"domains,":[51,109],"leveraging":[52],"word":[53,81],"embeddings":[54,67,127],"learned":[55],"from":[56,92],"observed":[57],"domain":[58,93],"names":[59,94],"DNS":[61],"queries":[62],"or":[63],"browsing":[64],"URLs.":[65],"are":[68],"constructed":[69],"with":[70],"Dom2Vec":[71],"(D2V),":[72],"novel":[74],"technique":[75],"which":[76],"builds":[77],"on":[78,102],"top":[79],"embedding":[82],"models":[83],"(e.g.,":[84],"Word2Vec)":[85],"to":[86],"map":[87],"words":[88],"tokens":[90],"extracted":[91],"into":[95],"highly":[96],"expressive":[97],"representations.":[98],"Through":[99],"experimental":[100],"evaluation":[101],"large-scale":[104],"dataset":[105],"almost":[107],"800,000":[108],"comprising":[110],"25":[111],"distinct":[112],"families":[113],"DGA":[115],"URLs,":[120],"we":[121],"demonstrate":[122],"the":[123,134],"goodness":[124],"D2V":[126],"detection,":[130],"particular":[132],"DGAs.":[137]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}