{"id":"https://openalex.org/W2744692361","doi":"https://doi.org/10.1145/3097983.3098193","title":"Automated Categorization of Onion Sites for Analyzing the Darkweb Ecosystem","display_name":"Automated Categorization of Onion Sites for Analyzing the Darkweb Ecosystem","publication_year":2017,"publication_date":"2017-08-04","ids":{"openalex":"https://openalex.org/W2744692361","doi":"https://doi.org/10.1145/3097983.3098193","mag":"2744692361"},"language":"en","primary_location":{"id":"doi:10.1145/3097983.3098193","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102095407","display_name":"Shalini Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shalini Ghosh","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103245820","display_name":"Ariyam Das","orcid":"https://orcid.org/0000-0003-0950-606X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariyam Das","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023691744","display_name":"Phil Porras","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phil Porras","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085002486","display_name":"Vinod Yegneswaran","orcid":"https://orcid.org/0000-0003-0718-6605"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinod Yegneswaran","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035466033","display_name":"Ashish Gehani","orcid":"https://orcid.org/0000-0002-3940-2467"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Gehani","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4516,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.94563154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1793","last_page":"1802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9997000098228455,"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":0.9997000098228455,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9994999766349792,"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7937361001968384},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5480270385742188},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.508873462677002},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5056824684143066},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.47995948791503906},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4760139584541321},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.46767908334732056},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4583977162837982},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4167829751968384},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37504348158836365},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35169151425361633},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33786651492118835},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2810487747192383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22449979186058044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937361001968384},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5480270385742188},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.508873462677002},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5056824684143066},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.47995948791503906},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4760139584541321},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.46767908334732056},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4583977162837982},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4167829751968384},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37504348158836365},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35169151425361633},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33786651492118835},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2810487747192383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22449979186058044},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3097983.3098193","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4039276700","display_name":null,"funder_award_id":"FA8750-14-C-0237","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G593455608","display_name":"TWC: Medium: Collaborative: HIMALAYAS: Hierarchical Machine Learning Stack for Fine-Grained Analysis of Malware Domain Groups","funder_award_id":"1314956","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W229583245","https://openalex.org/W790941020","https://openalex.org/W1568546821","https://openalex.org/W1574845294","https://openalex.org/W1574901103","https://openalex.org/W1636513602","https://openalex.org/W1855811457","https://openalex.org/W1880262756","https://openalex.org/W1978054023","https://openalex.org/W1983305247","https://openalex.org/W2010463775","https://openalex.org/W2013029404","https://openalex.org/W2023580532","https://openalex.org/W2027719216","https://openalex.org/W2049633694","https://openalex.org/W2064675550","https://openalex.org/W2071376663","https://openalex.org/W2080429359","https://openalex.org/W2102524069","https://openalex.org/W2108331487","https://openalex.org/W2110441437","https://openalex.org/W2113341218","https://openalex.org/W2115665694","https://openalex.org/W2124658502","https://openalex.org/W2127218421","https://openalex.org/W2134089414","https://openalex.org/W2139956879","https://openalex.org/W2163007546","https://openalex.org/W2165599843","https://openalex.org/W2241217517","https://openalex.org/W2269520727","https://openalex.org/W2275625487","https://openalex.org/W2283045161","https://openalex.org/W2307316789","https://openalex.org/W2396652156","https://openalex.org/W2952930881","https://openalex.org/W3034265065","https://openalex.org/W4245411633","https://openalex.org/W6603562897"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2291311298","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448"],"abstract_inverted_index":{"Onion":[0,95],"sites":[1,26,46,75,114],"on":[2,17,219,232],"the":[3,7,18,48,55,110,116,150,159,206,224,233,241,247,285],"darkweb":[4,49],"operate":[5],"using":[6],"Tor":[8],"Hidden":[9],"Service":[10],"(HS)":[11],"protocol":[12],"to":[13,27,36,54,104,162,167,197,201,239],"shield":[14],"their":[15],"locations":[16],"Internet,":[19],"which":[20,132],"(among":[21],"other":[22],"features)":[23],"enables":[24],"these":[25],"host":[28],"malicious":[29],"and":[30,39,42,58,70,143,227,279],"illegal":[31],"content":[32,72,111,166,204],"while":[33,260],"being":[34],"resistant":[35],"legal":[37],"action":[38],"seizure.":[40],"Identifying":[41],"monitoring":[43],"such":[44],"illicit":[45],"in":[47,115,205],"is":[50,176],"of":[51,109,112,170,208,217,243,284],"high":[52],"relevance":[53],"Computer":[56],"Security":[57],"Law":[59],"Enforcement":[60],"communities.":[61],"We":[62,271],"have":[63],"developed":[64,103],"an":[65,257],"automated":[66],"infrastructure":[67],"that":[68,146,157,183],"crawls":[69],"indexes":[71],"from":[73,187,194,223],"onion":[74,113,164,203,220],"into":[76],"a":[77,98,106,126,153,168,179,252,263],"large-scale":[78],"data":[79,175],"repository,":[80,226],"called":[81],"LIGHTS,":[82],"with":[83],"over":[84,256,266],"100M":[85],"pages.":[86],"In":[87],"this":[88],"paper":[89,213],"we":[90],"describe":[91],"Automated":[92],"Tool":[93],"for":[94,136,149],"Labeling":[96],"(ATOL),":[97],"novel":[99,127],"scalable":[100],"analysis":[101],"service":[102],"conduct":[105],"thematic":[107],"assessment":[108],"LIGHTS":[117,225,248,286],"repository.":[118],"ATOL":[119,218,275],"has":[120,276],"three":[121],"core":[122],"components":[123],"--":[124],"(a)":[125],"keyword":[128],"discovery":[129],"mechanism":[130],"(ATOLKeyword)":[131],"extends":[133],"analyst-provided":[134,258],"keywords":[135,145,161],"different":[137],"categories":[138,171],"by":[139],"suggesting":[140],"new":[141],"descriptive":[142],"discriminative":[144],"are":[147],"relevant":[148],"categories;":[151],"(b)":[152],"classification":[154],"framework":[155,181],"(ATOLClassify)":[156],"uses":[158],"discovered":[160],"map":[163],"site":[165],"set":[169],"when":[172],"sufficient":[173,209],"labeled":[174],"available;":[177],"(c)":[178],"clustering":[180,269],"(ATOLCluster)":[182],"can":[184],"leverage":[185],"information":[186],"multiple":[188],"external":[189],"heterogeneous":[190],"knowledge":[191],"sources,":[192],"ranging":[193],"domain":[195],"expertise":[196],"Bitcoin":[198],"transaction":[199],"data,":[200],"categorize":[202],"absence":[207],"supervised":[210],"data.":[211],"The":[212],"presents":[214],"empirical":[215],"results":[216],"datasets":[221],"derived":[222],"additionally":[228],"benchmarks":[229],"ATOL's":[230],"algorithms":[231],"publicly":[234],"available":[235],"20":[236],"Newsgroups":[237],"dataset":[238],"demonstrate":[240],"reproducibility":[242],"its":[244],"results.":[245],"On":[246],"dataset,":[249],"ATOLClassify":[250],"gives":[251,262],"12%":[253],"performance":[254],"gain":[255],"baseline,":[259],"ATOLCluster":[261],"7%":[264],"improvement":[265],"state-of-the-art":[267],"semi-supervised":[268],"algorithms.":[270],"also":[272],"discuss":[273],"how":[274],"been":[277],"deployed":[278],"externally":[280],"evaluated,":[281],"as":[282],"part":[283],"system.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}