{"id":"https://openalex.org/W3094518463","doi":"https://doi.org/10.1145/3419394.3423653","title":"Identifying Sensitive URLs at Web-Scale","display_name":"Identifying Sensitive URLs at Web-Scale","publication_year":2020,"publication_date":"2020-10-22","ids":{"openalex":"https://openalex.org/W3094518463","doi":"https://doi.org/10.1145/3419394.3423653","mag":"3094518463"},"language":"en","primary_location":{"id":"doi:10.1145/3419394.3423653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3419394.3423653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Internet Measurement Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ktisis.cut.ac.cy/handle/10488/23112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079790457","display_name":"Srdjan Matic","orcid":"https://orcid.org/0000-0003-2822-3970"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Srdjan Matic","raw_affiliation_strings":["TU Berlin"],"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026199839","display_name":"Costas Iordanou","orcid":"https://orcid.org/0000-0002-7424-7482"},"institutions":[{"id":"https://openalex.org/I163151358","display_name":"Cyprus University of Technology","ror":"https://ror.org/05qt8tf94","country_code":"CY","type":"education","lineage":["https://openalex.org/I163151358"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Costas Iordanou","raw_affiliation_strings":["Cyprus University of Technology"],"affiliations":[{"raw_affiliation_string":"Cyprus University of Technology","institution_ids":["https://openalex.org/I163151358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005247877","display_name":"Georgios Smaragdakis","orcid":"https://orcid.org/0000-0002-4127-3617"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgios Smaragdakis","raw_affiliation_strings":["TU Berlin"],"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010172378","display_name":"Nikolaos Laoutaris","orcid":"https://orcid.org/0000-0002-7361-106X"},"institutions":[{"id":"https://openalex.org/I2802499160","display_name":"IMDEA Networks","ror":"https://ror.org/04mm9fg30","country_code":"ES","type":"facility","lineage":["https://openalex.org/I105140100","https://openalex.org/I2802499160"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nikolaos Laoutaris","raw_affiliation_strings":["IMDEA Networks Institute"],"affiliations":[{"raw_affiliation_string":"IMDEA Networks Institute","institution_ids":["https://openalex.org/I2802499160"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079790457"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":3.3386,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93712246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"619","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9939000010490417,"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":0.9912999868392944,"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/computer-science","display_name":"Computer science","score":0.7449392676353455},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6766509413719177},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.604637861251831},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.529197096824646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5040261149406433},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46895259618759155},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3298184871673584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26400578022003174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449392676353455},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6766509413719177},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.604637861251831},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.529197096824646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5040261149406433},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46895259618759155},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3298184871673584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26400578022003174},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3419394.3423653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3419394.3423653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Internet Measurement Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:ktisis.cut.ac.cy:10488/23112","is_oa":true,"landing_page_url":"https://ktisis.cut.ac.cy/handle/10488/23112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400897","display_name":"Ktisis at Cyprus University of Technology (Cyprus University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I163151358","host_organization_name":"Cyprus University of Technology","host_organization_lineage":["https://openalex.org/I163151358"],"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":"","raw_type":"conferenceObject"},{"id":"pmh:oai:ktisis.cut.ac.cy:20.500.14279/23112","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14279/23112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400897","display_name":"Ktisis at Cyprus University of Technology (Cyprus University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I163151358","host_organization_name":"Cyprus University of Technology","host_organization_lineage":["https://openalex.org/I163151358"],"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":"","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:ktisis.cut.ac.cy:10488/23112","is_oa":true,"landing_page_url":"https://ktisis.cut.ac.cy/handle/10488/23112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400897","display_name":"Ktisis at Cyprus University of Technology (Cyprus University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I163151358","host_organization_name":"Cyprus University of Technology","host_organization_lineage":["https://openalex.org/I163151358"],"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":"","raw_type":"conferenceObject"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G3384657666","display_name":"PIMCITY: BUILDING THE NEXT GENERATION PERSONAL DATA PLATFORMS","funder_award_id":"871370","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4702409769","display_name":null,"funder_award_id":"RC-StG","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7441628564","display_name":"Resolving the Tussle in the Internet: Mapping, Architecture, and Policy Making","funder_award_id":"679158","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"},{"id":"https://openalex.org/F4320324094","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W845431725","https://openalex.org/W1562129026","https://openalex.org/W1972848388","https://openalex.org/W1978394996","https://openalex.org/W1980462902","https://openalex.org/W1992470436","https://openalex.org/W1994485670","https://openalex.org/W2011265791","https://openalex.org/W2023559190","https://openalex.org/W2028509822","https://openalex.org/W2032304665","https://openalex.org/W2039844768","https://openalex.org/W2056234582","https://openalex.org/W2065055142","https://openalex.org/W2067223933","https://openalex.org/W2067698488","https://openalex.org/W2124993430","https://openalex.org/W2140785063","https://openalex.org/W2143774317","https://openalex.org/W2150827944","https://openalex.org/W2153579005","https://openalex.org/W2159548212","https://openalex.org/W2159764755","https://openalex.org/W2161367368","https://openalex.org/W2161498199","https://openalex.org/W2489352404","https://openalex.org/W2535603283","https://openalex.org/W2552004720","https://openalex.org/W2561412020","https://openalex.org/W2610602442","https://openalex.org/W2740383888","https://openalex.org/W2758544228","https://openalex.org/W2770885069","https://openalex.org/W2784134919","https://openalex.org/W2785401534","https://openalex.org/W2788461260","https://openalex.org/W2789468576","https://openalex.org/W2796498984","https://openalex.org/W2797171593","https://openalex.org/W2888846082","https://openalex.org/W2890931111","https://openalex.org/W2898364732","https://openalex.org/W2902322559","https://openalex.org/W2905328986","https://openalex.org/W2912826586","https://openalex.org/W2924423994","https://openalex.org/W2937423263","https://openalex.org/W2949547296","https://openalex.org/W2958793707","https://openalex.org/W2962940036","https://openalex.org/W2963150549","https://openalex.org/W2966457557","https://openalex.org/W2968744947","https://openalex.org/W2971437238","https://openalex.org/W2980748551","https://openalex.org/W3100240544","https://openalex.org/W3105625590","https://openalex.org/W4285719527","https://openalex.org/W6679942958"],"related_works":["https://openalex.org/W4389910871","https://openalex.org/W2557205449","https://openalex.org/W2086677144","https://openalex.org/W2892196156","https://openalex.org/W3130085708","https://openalex.org/W3111843495","https://openalex.org/W4388444894","https://openalex.org/W4287998529","https://openalex.org/W4287328308","https://openalex.org/W2000745862"],"abstract_inverted_index":{"Several":[0],"data":[1,10,100],"protection":[2,44],"laws":[3],"include":[4],"special":[5],"provisions":[6],"for":[7,30,97,106,139],"protecting":[8],"personal":[9],"relating":[11],"to":[12,65,91,101,137,180,184],"religion,":[13],"health,":[14],"sexual":[15],"orientation,":[16],"and":[17,36,75,122],"other":[18],"sensitive":[19,26,58,82,107,116,126,140,161,171,189],"categories.":[20],"Having":[21],"a":[22,103,143],"well-defined":[23],"list":[24],"of":[25,41,53,145,176,196],"categories":[27,127],"is":[28,62],"sufficient":[29],"filing":[31,76],"complaints":[32,77],"manually,":[33],"conducting":[34],"investigations,":[35],"prosecuting":[37],"cases":[38,88],"in":[39,142,163,188],"courts":[40],"law.":[42],"Data":[43],"laws,":[45],"however,":[46],"do":[47],"not":[48],"define":[49],"explicitly":[50],"what":[51],"type":[52],"content":[54],"falls":[55],"under":[56],"each":[57],"category.":[59],"Therefore,":[60],"it":[61],"unclear":[63],"how":[64],"implement":[66],"proactive":[67],"measures":[68],"such":[69,86],"as":[70],"informing":[71],"users,":[72],"blocking":[73],"trackers,":[74],"automatically":[78],"when":[79],"users":[80],"visit":[81],"domains.":[83,168],"To":[84],"empower":[85],"use":[87,134,185],"we":[89],"turn":[90],"the":[92,151,197],"Curlie.org":[93],"crowdsourced":[94],"taxonomy":[95],"project":[96],"drawing":[98],"training":[99],"build":[102],"text":[104],"classifier":[105,113,136],"URLs.":[108],"We":[109,132,155],"demonstrate":[110],"that":[111,182],"our":[112,135],"can":[114],"identify":[115,156],"URLs":[117,141,148,162,178],"with":[118,128,192],"accuracy":[119,129],"above":[120,130],"88%,":[121],"even":[123],"recognize":[124],"specific":[125],"90%.":[131],"then":[133],"search":[138],"corpus":[144],"1":[146],"Billion":[147],"collected":[149],"by":[150],"Common":[152],"Crawl":[153],"project.":[154],"more":[157,164,173],"than":[158,165,174],"155":[159],"millions":[160],"4":[166],"million":[167],"Despite":[169],"their":[170],"nature,":[172],"30%":[175],"these":[177],"belong":[179],"domains":[181],"fail":[183],"HTTPS.":[186],"Also,":[187],"web":[190],"pages":[191],"third-party":[193],"cookies,":[194],"87%":[195],"third-parties":[198],"set":[199],"at":[200],"least":[201],"one":[202],"persistent":[203],"cookie.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
