{"id":"https://openalex.org/W2914403931","doi":"https://doi.org/10.1109/bigdata.2018.8622469","title":"Collecting Cyber Threat Intelligence from Hacker Forums via a Two-Stage, Hybrid Process using Support Vector Machines and Latent Dirichlet Allocation","display_name":"Collecting Cyber Threat Intelligence from Hacker Forums via a Two-Stage, Hybrid Process using Support Vector Machines and Latent Dirichlet Allocation","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914403931","doi":"https://doi.org/10.1109/bigdata.2018.8622469","mag":"2914403931"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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/A5037316127","display_name":"Isuf Deliu","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Isuf Deliu","raw_affiliation_strings":["Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gj\u00f8vik, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gj\u00f8vik, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072253457","display_name":"Carl Leichter","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Carl Leichter","raw_affiliation_strings":["Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gj\u00f8vik, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gj\u00f8vik, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028698767","display_name":"Katrin Franke","orcid":"https://orcid.org/0000-0002-4899-9410"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Katrin Franke","raw_affiliation_strings":["Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gj\u00f8vik, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gj\u00f8vik, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037316127"],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":7.8538,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97585215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5008","last_page":"5013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9994000196456909,"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":0.9994000196456909,"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9990000128746033,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/hacker","display_name":"Hacker","score":0.8669360876083374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779005765914917},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7666423320770264},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.6581012606620789},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5904342532157898},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.45868802070617676},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44587212800979614},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4128355085849762},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3629193902015686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32746896147727966},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24439314007759094}],"concepts":[{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.8669360876083374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779005765914917},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7666423320770264},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.6581012606620789},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5904342532157898},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.45868802070617676},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44587212800979614},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4128355085849762},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3629193902015686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32746896147727966},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24439314007759094},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1533605091","https://openalex.org/W1672113969","https://openalex.org/W1674074141","https://openalex.org/W1712618182","https://openalex.org/W1880262756","https://openalex.org/W2048195127","https://openalex.org/W2087347434","https://openalex.org/W2115994290","https://openalex.org/W2119821739","https://openalex.org/W2147152072","https://openalex.org/W2165599843","https://openalex.org/W2174706414","https://openalex.org/W2334889010","https://openalex.org/W2522581443","https://openalex.org/W2554200766","https://openalex.org/W2555449513","https://openalex.org/W2784295274","https://openalex.org/W2883522050","https://openalex.org/W2963980822","https://openalex.org/W2964051216","https://openalex.org/W4239510810","https://openalex.org/W4293469115","https://openalex.org/W4301680216","https://openalex.org/W6639619044","https://openalex.org/W6684489972","https://openalex.org/W6703074907"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"Traditional":[0],"security":[1,14,113,200],"controls,":[2],"such":[3,43,165],"as":[4,44,166],"firewalls,":[5],"anti-virus":[6],"and":[7,15,47,52,82,114,138,191],"IDS,":[8],"are":[9,108,128],"ill-equipped":[10],"to":[11,60,70,111,158,202],"help":[12,34],"IT":[13],"response":[16,53],"teams":[17,54],"keep":[18],"pace":[19],"with":[20,198],"the":[21,25,57,105,117,123,126,139],"rapid":[22],"evolution":[23],"of":[24,122],"cyber":[26,112],"threat":[27],"landscape.":[28],"Cyber":[29],"Threat":[30],"Intelligence":[31],"(CTI)":[32],"can":[33,55,195],"remediate":[35],"this":[36],"problem":[37],"by":[38,90],"exploiting":[39],"non-traditional":[40,74],"information":[41,161],"sources,":[42,75],"hacker":[45,101,156],"forums":[46],"\"dark-web\"":[48],"social":[49],"platforms.":[50],"Security":[51],"use":[56],"collected":[58],"intelligence":[59,193],"identify":[61],"emerging":[62],"threats.":[63],"Unfortunately,":[64],"when":[65],"manual":[66],"analysis":[67],"is":[68,77,183],"used":[69],"extract":[71,160],"CTI":[72],"from":[73,153],"it":[76],"a":[78,92],"time":[79],"consuming,":[80],"error-prone":[81],"resource":[83],"intensive":[84],"process.":[85],"We":[86,147],"address":[87],"these":[88],"issues":[89],"using":[91,151],"hybrid":[93],"Machine":[94],"Learning":[95],"model":[96],"that":[97,107,125,173,194],"automatically":[98,159],"searches":[99],"through":[100],"forum":[102],"posts,":[103],"identifies":[104],"posts":[106,119],"most":[109],"relevant":[110,118,190],"then":[115],"clusters":[116],"into":[120],"estimations":[121],"topics":[124],"hackers":[127],"discussing.":[129],"The":[130,178],"first":[131],"(identification)":[132],"stage":[133,142],"uses":[134,143],"Support":[135],"Vector":[136],"Machines":[137],"second":[140],"(clustering)":[141],"Latent":[144],"Dirichlet":[145],"Allocation.":[146],"tested":[148],"our":[149,181],"model,":[150],"data":[152],"an":[154,184],"actual":[155],"forum,":[157],"about":[162],"various":[163],"threats":[164],"leaked":[167],"credentials,":[168],"malicious":[169],"proxy":[170],"servers,":[171],"malware":[172],"evades":[174],"AV":[175],"detection,":[176],"etc.":[177],"results":[179],"demonstrate":[180],"method":[182],"effective":[185],"means":[186],"for":[187],"quickly":[188],"extracting":[189],"actionable":[192],"be":[196],"integrated":[197],"traditional":[199],"controls":[201],"increase":[203],"their":[204],"effectiveness.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
