{"id":"https://openalex.org/W4285410855","doi":"https://doi.org/10.5220/0011298600003283","title":"Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information","display_name":"Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285410855","doi":"https://doi.org/10.5220/0011298600003283"},"language":"en","primary_location":{"id":"doi:10.5220/0011298600003283","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011298600003283","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Conference on Security and Cryptography","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011298600003283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056162524","display_name":"Giuseppe Cascavilla","orcid":"https://orcid.org/0000-0002-0724-3772"},"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":"Giuseppe Cascavilla","raw_affiliation_strings":["Eindhoven University of Technology, Jheronimus Academy of Data Science, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Jheronimus Academy of Data Science, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014169292","display_name":"Gemma Catolino","orcid":"https://orcid.org/0000-0002-4689-3401"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gemma Catolino","raw_affiliation_strings":["Tilburg University, Jheronimus Academy of Data Science, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tilburg University, Jheronimus Academy of Data Science, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016548184","display_name":"Mirella Sangiovanni","orcid":null},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mirella Sangiovanni","raw_affiliation_strings":["Tilburg University, Jheronimus Academy of Data Science, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tilburg University, Jheronimus Academy of Data Science, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I193700539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3322,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.94812408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"620","last_page":"626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9987999796867371,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530891299247742},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5895949602127075},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5034343600273132},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5002386569976807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48708510398864746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4366816282272339},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43278759717941284},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36675363779067993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530891299247742},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5895949602127075},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5034343600273132},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5002386569976807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48708510398864746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4366816282272339},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43278759717941284},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36675363779067993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011298600003283","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011298600003283","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Conference on Security and Cryptography","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.04944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04944","pdf_url":"https://arxiv.org/pdf/2312.04944","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0011298600003283","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011298600003283","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Conference on Security and Cryptography","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1855811457","https://openalex.org/W2008609081","https://openalex.org/W2014545475","https://openalex.org/W2059304719","https://openalex.org/W2080429359","https://openalex.org/W2167004467","https://openalex.org/W2244440518","https://openalex.org/W2566838294","https://openalex.org/W2738067371","https://openalex.org/W2741026990","https://openalex.org/W2791710883","https://openalex.org/W2909195503","https://openalex.org/W2920344165","https://openalex.org/W3133650126","https://openalex.org/W4231510805","https://openalex.org/W4281626839","https://openalex.org/W4389749033"],"related_works":["https://openalex.org/W4250539519","https://openalex.org/W4294018197","https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W3112355890","https://openalex.org/W2613685774","https://openalex.org/W2000745862","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"at":[3],"expanding":[4],"previous":[5],"works":[6],"done":[7],"in":[8],"the":[9,82,89,99,103,109],"context":[10],"of":[11,25,92,111,117],"illegal":[12,73],"activities":[13,74],"classification,":[14],"performing":[15],"three":[16],"different":[17],"steps.":[18],"First,":[19],"we":[20,33,70],"created":[21],"a":[22,57],"heterogeneous":[23],"dataset":[24],"113995":[26],"onion":[27],"sites":[28],"and":[29,50,85,108,115],"dark":[30,104],"marketplaces.":[31],"Then,":[32],"compared":[34],"pre-trained":[35],"transferable":[36],"models,":[37],"i.e.,":[38],"ULMFit":[39],"(Universal":[40],"Language":[41],"Model":[42],"Fine-tuning),":[43],"Bert":[44,97],"(Bidirectional":[45],"Encoder":[46],"Representations":[47],"from":[48],"Transformers),":[49],"RoBERTa":[51],"(Robustly":[52],"optimized":[53],"BERT":[54],"approach)":[55],"with":[56,113],"traditional":[58],"text":[59],"classification":[60,75],"approach":[61],"like":[62],"LSTM":[63],"(Long":[64],"short-term":[65],"memory)":[66],"neural":[67],"networks.":[68],"Finally,":[69],"developed":[71],"two":[72],"approaches,":[76],"one":[77,86],"for":[78,87],"illicit":[79],"content":[80,107],"on":[81],"Dark":[83],"Web":[84],"identifying":[88],"specific":[90],"types":[91,110],"drugs.":[93],"Results":[94],"show":[95],"that":[96],"obtained":[98],"best":[100],"approach,":[101],"classifying":[102],"web's":[105],"general":[106],"Drugs":[112],"96.08%":[114],"91.98%":[116],"accuracy.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2022-07-14T00:00:00"}