{"id":"https://openalex.org/W2608201337","doi":"https://doi.org/10.23919/tma.2017.8002914","title":"FilteredWeb: A framework for the automated search-based discovery of blocked URLs","display_name":"FilteredWeb: A framework for the automated search-based discovery of blocked URLs","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2608201337","doi":"https://doi.org/10.23919/tma.2017.8002914","mag":"2608201337"},"language":"en","primary_location":{"id":"doi:10.23919/tma.2017.8002914","is_oa":false,"landing_page_url":"https://doi.org/10.23919/tma.2017.8002914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Network Traffic Measurement and Analysis Conference (TMA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1704.07185","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050960947","display_name":"Alexander Darer","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Darer","raw_affiliation_strings":["University of Oxford, Oxford, Oxfordshire, GB","Dept. of Comput. Sci., Univ. of Oxford, Oxford, , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, Oxfordshire, GB","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Oxford, Oxford, , UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053571125","display_name":"Oliver Farnan","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Farnan","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, UK","Dept. of Comput. Sci., Univ. of Oxford, Oxford, , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Oxford, Oxford, , UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043144947","display_name":"Joss Wright","orcid":"https://orcid.org/0000-0001-5237-3309"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joss Wright","raw_affiliation_strings":["Oxford Internet Institute, University of Oxford, Oxford, UK","Oxford Internet Institute , University of Oxford , Oxford , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford Internet Institute, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Internet Institute , University of Oxford , Oxford , UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0256,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89545522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9962000250816345,"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":0.7851800918579102},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7367451190948486},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6980504989624023},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6296958923339844},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.6273918151855469},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.6218907833099365},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5788843631744385},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5380958914756775},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5047174692153931},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.48971226811408997},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46575552225112915},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4147428274154663},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4137353003025055},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.35561996698379517},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08577936887741089}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851800918579102},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7367451190948486},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6980504989624023},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6296958923339844},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.6273918151855469},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.6218907833099365},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5788843631744385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5380958914756775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5047174692153931},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.48971226811408997},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46575552225112915},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4147428274154663},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4137353003025055},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.35561996698379517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08577936887741089},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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":5,"locations":[{"id":"doi:10.23919/tma.2017.8002914","is_oa":false,"landing_page_url":"https://doi.org/10.23919/tma.2017.8002914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Network Traffic Measurement and Analysis Conference (TMA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.07185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.07185","pdf_url":"https://arxiv.org/pdf/1704.07185","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:6321b48a-9a84-4452-8e2b-9e0ccb59ff67","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:6321b48a-9a84-4452-8e2b-9e0ccb59ff67","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"},{"id":"doi:10.48550/arxiv.1704.07185","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.07185","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2608201337","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1704.07185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.07185","pdf_url":"https://arxiv.org/pdf/1704.07185","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2608201337.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W637237343","https://openalex.org/W1736726159","https://openalex.org/W1830741683","https://openalex.org/W1880262756","https://openalex.org/W1956559956","https://openalex.org/W1968355613","https://openalex.org/W2012152947","https://openalex.org/W2087027277","https://openalex.org/W2105151076","https://openalex.org/W2126053700","https://openalex.org/W2134747589","https://openalex.org/W2158269836","https://openalex.org/W2160792759","https://openalex.org/W2168006138","https://openalex.org/W2201189541","https://openalex.org/W2315475239","https://openalex.org/W2397812883","https://openalex.org/W2400899155","https://openalex.org/W2402831641","https://openalex.org/W2535378852","https://openalex.org/W2554901227","https://openalex.org/W2891373873","https://openalex.org/W3124321814","https://openalex.org/W4243774931","https://openalex.org/W6637969322","https://openalex.org/W6638652613","https://openalex.org/W6639619044","https://openalex.org/W6676147248","https://openalex.org/W6683066688","https://openalex.org/W6686565904","https://openalex.org/W6712454212","https://openalex.org/W6713556645","https://openalex.org/W6714279744","https://openalex.org/W6727023368"],"related_works":["https://openalex.org/W2620864756","https://openalex.org/W2198753417","https://openalex.org/W2296631386","https://openalex.org/W2183598948","https://openalex.org/W2187646317","https://openalex.org/W2148738951","https://openalex.org/W2550267965","https://openalex.org/W2186666332","https://openalex.org/W2850913","https://openalex.org/W2185236059","https://openalex.org/W3149973147","https://openalex.org/W3134042355","https://openalex.org/W1966772254","https://openalex.org/W2311564458","https://openalex.org/W596393722","https://openalex.org/W2187508687","https://openalex.org/W1578399205","https://openalex.org/W995007446","https://openalex.org/W2305934143","https://openalex.org/W3256017"],"abstract_inverted_index":{"Various":[0],"methods":[1],"have":[2],"been":[3],"proposed":[4],"for":[5,16,30,57,97,109],"creating":[6],"and":[7,113,235],"maintaining":[8],"lists":[9],"of":[10,18,32,61,68,104,111,132,152,166,186,201,209,219,232,251],"potentially":[11],"filtered":[12,45,63,88,128,155,226,233],"URLs":[13,103],"to":[14,71,81,125,136,162,178,222,242],"allow":[15],"measurement":[17],"ongoing":[19,164],"internet":[20,167],"censorship":[21],"around":[22],"the":[23,59,66,95,123,143,163,195,202,210,217,236,249,252],"world.":[24],"Whilst":[25],"testing":[26],"a":[27,54,139,159],"known":[28,87],"resource":[29],"evidence":[31,110],"filtering":[33,168],"can":[34],"be":[35,119],"relatively":[36],"simple,":[37],"given":[38],"appropriate":[39],"vantage":[40],"points,":[41],"discovering":[42,62],"previously":[43,153],"unknown":[44,154],"web":[46,89,98,156],"resources":[47,64,117],"remains":[48],"an":[49],"open":[50],"challenge.":[51],"We":[52],"present":[53],"novel":[55],"framework":[56,221],"automating":[58],"process":[60],"through":[65],"use":[67],"adaptive":[69],"queries":[70],"well-known":[72],"search":[73,99,237],"engines.":[74],"Our":[75,130],"system":[76,124,175],"applies":[77],"information":[78],"retrieval":[79],"algorithms":[80],"isolate":[82],"characteristic":[83],"linguistic":[84],"patterns":[85],"in":[86,194,257],"pages;":[90],"these":[91,105],"are":[92,107,207],"used":[93,177,241],"as":[94,138,169,185],"basis":[96],"queries.":[100],"The":[101],"resulting":[102],"searches":[106],"checked":[108],"filtering,":[112],"newly":[114],"discovered":[115],"blocked":[116,256],"will":[118],"fed":[120],"back":[121],"into":[122,248],"detect":[126],"further":[127,246],"content.":[129,227],"implementation":[131],"this":[133,174,220],"framework,":[134],"applied":[135],"China":[137,184],"case":[140],"study,":[141],"shows":[142],"approach":[144],"is":[145],"demonstrably":[146],"effective":[147],"at":[148],"detecting":[149],"significant":[150,160],"numbers":[151],"pages,":[157],"making":[158],"contribution":[161],"detection":[165],"it":[170],"develops.":[171],"When":[172],"deployed,":[173],"was":[176],"discover":[179,243],"1355":[180],"poisoned":[181],"domains":[182,214],"within":[183],"Feb":[187],"2017":[188],"\u2014":[189],"30":[190],"times":[191],"more":[192,224],"than":[193],"most":[196],"widely-used":[197],"published":[198],"filter":[199],"list":[200],"time.":[203],"Of":[204],"these,":[205],"759":[206],"outside":[208],"Alexa":[211],"Top":[212],"1000":[213],"list,":[215],"demonstrating":[216],"capability":[218],"find":[223],"obscure":[225],"Further,":[228],"our":[229],"initial":[230],"analysis":[231],"URLs,":[234],"terms":[238],"that":[239],"were":[240],"them,":[244],"gives":[245],"insight":[247],"nature":[250],"content":[253],"currently":[254],"being":[255],"China.":[258]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
