{"id":"https://openalex.org/W4379528892","doi":"https://doi.org/10.1109/ecrime57793.2022.10142081","title":"THREAT/crawl: a Trainable, Highly-Reusable, and Extensible Automated Method and Tool to Crawl Criminal Underground Forums","display_name":"THREAT/crawl: a Trainable, Highly-Reusable, and Extensible Automated Method and Tool to Crawl Criminal Underground Forums","publication_year":2022,"publication_date":"2022-11-30","ids":{"openalex":"https://openalex.org/W4379528892","doi":"https://doi.org/10.1109/ecrime57793.2022.10142081"},"language":"en","primary_location":{"id":"doi:10.1109/ecrime57793.2022.10142081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecrime57793.2022.10142081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 APWG Symposium on Electronic Crime Research (eCrime)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/379146626/THREAT_crawl_a_Trainable_Highly-Reusable_and_Extensible_Automated_Method_and_Tool_to_Crawl_Criminal_Underground_Forums.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014328930","display_name":"Michele Campobasso","orcid":"https://orcid.org/0000-0002-5247-7711"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Michele Campobasso","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047635330","display_name":"Luca Allodi","orcid":"https://orcid.org/0000-0003-1600-0868"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Luca Allodi","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014328930"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.8933,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73635075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9962999820709229,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8570699095726013},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7700275182723999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261211276054382},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5919851660728455},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47421908378601074}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8570699095726013},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7700275182723999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261211276054382},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5919851660728455},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47421908378601074},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ecrime57793.2022.10142081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecrime57793.2022.10142081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 APWG Symposium on Electronic Crime Research (eCrime)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/1c8a5598-19a0-4afd-b3c2-b95715f58252","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/1c8a5598-19a0-4afd-b3c2-b95715f58252","pdf_url":"https://pure.tue.nl/ws/files/379146626/THREAT_crawl_a_Trainable_Highly-Reusable_and_Extensible_Automated_Method_and_Tool_to_Crawl_Criminal_Underground_Forums.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Campobasso, M & Allodi, L 2023, THREAT/crawl : a Trainable, Highly-Reusable, and Extensible Automated Method and Tool to Crawl Criminal Underground Forums. in Proceedings of the 2022 APWG Symposium on Electronic Crime Research, eCrime 2022., 10142081, Institute of Electrical and Electronics Engineers, 2022 APWG Symposium on Electronic Crime Research (eCrime), Boston, United States, 30/11/22. https://doi.org/10.1109/eCrime57793.2022.10142081","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:publications/1c8a5598-19a0-4afd-b3c2-b95715f58252","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/1c8a5598-19a0-4afd-b3c2-b95715f58252","pdf_url":"https://pure.tue.nl/ws/files/379146626/THREAT_crawl_a_Trainable_Highly-Reusable_and_Extensible_Automated_Method_and_Tool_to_Crawl_Criminal_Underground_Forums.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Campobasso, M & Allodi, L 2023, THREAT/crawl : a Trainable, Highly-Reusable, and Extensible Automated Method and Tool to Crawl Criminal Underground Forums. in Proceedings of the 2022 APWG Symposium on Electronic Crime Research, eCrime 2022., 10142081, Institute of Electrical and Electronics Engineers, 2022 APWG Symposium on Electronic Crime Research (eCrime), Boston, United States, 30/11/22. https://doi.org/10.1109/eCrime57793.2022.10142081","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5937870420","display_name":null,"funder_award_id":"NWA.1162.18.301","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G620320933","display_name":null,"funder_award_id":"ITEA191010","funder_id":"https://openalex.org/F4320314237","funder_display_name":"Rijksdienst voor Ondernemend Nederland"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320313144","display_name":"ITEA","ror":null},{"id":"https://openalex.org/F4320314237","display_name":"Rijksdienst voor Ondernemend Nederland","ror":null},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320325600","display_name":"ITEA3","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379528892.pdf","grobid_xml":"https://content.openalex.org/works/W4379528892.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1559760877","https://openalex.org/W1575663745","https://openalex.org/W1976216148","https://openalex.org/W2009229808","https://openalex.org/W2113341218","https://openalex.org/W2250463012","https://openalex.org/W2295645274","https://openalex.org/W2414519424","https://openalex.org/W2472362036","https://openalex.org/W2765751196","https://openalex.org/W2766615649","https://openalex.org/W2798110387","https://openalex.org/W2800652629","https://openalex.org/W2891270452","https://openalex.org/W2917807496","https://openalex.org/W2940555334","https://openalex.org/W2963980822","https://openalex.org/W2964274850","https://openalex.org/W2973219882","https://openalex.org/W3045686863","https://openalex.org/W3084102164","https://openalex.org/W3094434138","https://openalex.org/W3101360328","https://openalex.org/W3101921171","https://openalex.org/W3162913697","https://openalex.org/W6781614840"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2084213350","https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2152505903"],"abstract_inverted_index":{"Collecting":[0],"data":[1],"on":[2],"underground":[3,118],"criminal":[4],"communities":[5,18],"is":[6],"highly":[7,71],"valuable":[8],"both":[9],"for":[10,44,69],"security":[11,14],"research":[12],"and":[13,37,54,66,91,95,105],"operations.":[15],"Unfortunately":[16],"these":[17],"live":[19],"within":[20],"a":[21,64,70,77,113],"constellation":[22],"of":[23,41,80,109,115],"diverse":[24],"online":[25],"forums":[26],"that":[27,74],"are":[28],"difficult":[29],"to":[30],"infiltrate,":[31],"may":[32],"adopt":[33],"crawling":[34,89],"monitoring":[35],"countermeasures,":[36],"require":[38],"the":[39,49,88,98],"development":[40],"ad-hoc":[42],"scrapers":[43],"each":[45],"different":[46],"community,":[47],"making":[48],"endeavour":[50],"increasingly":[51],"technically":[52],"challenging,":[53],"potentially":[55],"expensive.":[56],"To":[57],"address":[58],"this":[59],"problem":[60],"we":[61],"propose":[62],"THREAT/crawl,":[63],"method":[65],"prototype":[67,111],"tool":[68],"reusable":[72],"crawler":[73],"can":[75,84,92],"learn":[76],"wide":[78],"range":[79,114],"(arbitrary)":[81],"forum":[82],"structures,":[83],"remain":[85],"under-the-radar":[86],"during":[87],"activity":[90],"be":[93],"extended":[94],"configured":[96],"at":[97],"user":[99],"will.":[100],"We":[101],"showcase":[102],"THREAT/crawl":[103],"capabilities":[104],"provide":[106],"prime":[107],"evaluation":[108],"our":[110],"against":[112],"active,":[116],"live,":[117],"communities.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}