乐胖代购免代理版

{"id":"https://openalex.org/W2946113142","doi":"https://doi.org/10.1145/3336937.3336940","title":"Precise Detection of Content Reuse in the Web","display_name":"Precise Detection of Content Reuse in the Web","publication_year":2019,"publication_date":"2019-05-21","ids":{"openalex":"https://openalex.org/W2946113142","doi":"https://doi.org/10.1145/3336937.3336940","mag":"2946113142"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3336937.3336940","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3336937.3336940","source":{"id":"https://openalex.org/S66039016","display_name":"ACM SIGCOMM Computer Communication Review","issn_l":"0146-4833","issn":["0146-4833","1943-5819"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3336937.3336940","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013943183","display_name":"Calvin Ardi","orcid":"https://orcid.org/0000-0001-6994-9538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Calvin Ardi","raw_affiliation_strings":["USC/Information Sciences Institute"],"affiliations":[{"raw_affiliation_string":"USC/Information Sciences Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090014731","display_name":"John Heidemann","orcid":"https://orcid.org/0000-0002-1225-7562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Heidemann","raw_affiliation_strings":["USC/Information Sciences Institute"],"affiliations":[{"raw_affiliation_string":"USC/Information Sciences Institute","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.055,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.750344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":77,"max":79},"biblio":{"volume":"49","issue":"2","first_page":"9","last_page":"24"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998,"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":0.9998,"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":0.9992,"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":0.9912,"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/copying","display_name":"Copying","score":0.61265326},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.47772285},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4616102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85612214},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.61265326},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5527566},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48668247},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.47772285},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4616102},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4570861},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.44132075},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.39766246},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3965608},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.19537464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12206203},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3336937.3336940","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3336937.3336940","source":{"id":"https://openalex.org/S66039016","display_name":"ACM SIGCOMM Computer Communication Review","issn_l":"0146-4833","issn":["0146-4833","1943-5819"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3336937.3336940","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3336937.3336940","source":{"id":"https://openalex.org/S66039016","display_name":"ACM SIGCOMM Computer Communication Review","issn_l":"0146-4833","issn":["0146-4833","1943-5819"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":40,"referenced_works":["https://openalex.org/W1509629370","https://openalex.org/W1537134536","https://openalex.org/W1613836731","https://openalex.org/W1623072288","https://openalex.org/W1639305476","https://openalex.org/W1847423537","https://openalex.org/W1968197683","https://openalex.org/W1977729554","https://openalex.org/W1984287486","https://openalex.org/W1988068423","https://openalex.org/W1993865637","https://openalex.org/W200005393","https://openalex.org/W2012833704","https://openalex.org/W2026968007","https://openalex.org/W2048606985","https://openalex.org/W2064716575","https://openalex.org/W2066636486","https://openalex.org/W2067432306","https://openalex.org/W2071928865","https://openalex.org/W2085922539","https://openalex.org/W2089994405","https://openalex.org/W2097125878","https://openalex.org/W2109803107","https://openalex.org/W2123845384","https://openalex.org/W2145349611","https://openalex.org/W2146729596","https://openalex.org/W2152565070","https://openalex.org/W2156204309","https://openalex.org/W2156719566","https://openalex.org/W2167302605","https://openalex.org/W2169189540","https://openalex.org/W2170037597","https://openalex.org/W2173213060","https://openalex.org/W2751437099","https://openalex.org/W2894806357","https://openalex.org/W2913932916","https://openalex.org/W4231138846","https://openalex.org/W4241622387","https://openalex.org/W4243255773","https://openalex.org/W4250366158"],"related_works":["https://openalex.org/W4346570","https://openalex.org/W4308771405","https://openalex.org/W2897171874","https://openalex.org/W2550808318","https://openalex.org/W2544674189","https://openalex.org/W2367003870","https://openalex.org/W2278505189","https://openalex.org/W2262826214","https://openalex.org/W2012575882","https://openalex.org/W1987716395"],"abstract_inverted_index":{"With":[0],"vast":[1],"amount":[2],"of":[3,65,77,119,135,160,196,213],"content":[4,19,37,54,81,152],"online,":[5],"it":[6],"is":[7,28,82,122,181],"not":[8],"surprising":[9],"that":[10,29,73,116,137,175],"unscrupulous":[11],"entities":[12],"\"borrow\"":[13],"from":[14],"the":[15,56,59,88,133,154,163,179],"web":[16,102,171,180],"to":[17,48,61],"provide":[18],"for":[20,39,158],"advertisements,":[21],"link":[22],"farms,":[23],"and":[24,32,58,94,109,149,165],"spam.":[25],"Our":[26],"insight":[27],"cryptographic":[30,120],"hashing":[31,121],"fingerprinting":[33],"can":[34],"efficiently":[35],"identify":[36,85],"reuse":[38],"web-size":[40],"corpora.":[41],"We":[42,71,90,114,141,173],"develop":[43],"two":[44],"related":[45],"algorithms,":[46],"one":[47],"automatically":[49],"*discover*":[50],"previously":[51],"unknown":[52],"duplicate":[53],"in":[55,87,145,153,162,169,178],"web,":[57,155,164],"second":[60],"*precisely":[62],"detect*":[63],"copies":[64,159,195],"discovered":[66],"or":[67,191,203],"manually":[68],"identified":[69],"content.":[70],"show":[72,115,174],"*bad":[74],"neighborhoods*,":[75],"clusters":[76],"pages":[78],"where":[79],"copied":[80],"frequent,":[83],"help":[84],"copying":[86,177],"web.":[89],"verify":[91],"our":[92,117,143],"algorithm":[93],"its":[95],"choices":[96],"with":[97],"controlled":[98],"experiments":[99],"over":[100],"three":[101,146],"datasets:":[103],"Common":[104],"Crawl":[105],"(2009/10),":[106],"GeoCities":[107],"(1990s\u20132000s),":[108],"a":[110,170],"phishing":[111,167],"corpus":[112],"(2014).":[113],"use":[118],"much":[123],"more":[124],"precise":[125],"than":[126],"alternatives":[127],"such":[128],"as":[129],"locality-sensitive":[130],"hashing,":[131],"avoiding":[132],"thousands":[134],"false-positives":[136],"would":[138],"otherwise":[139],"occur.":[140],"apply":[142],"approach":[144],"systems:":[147],"discovering":[148],"detecting":[150,166,211],"duplicated":[151],"searching":[156],"explicitly":[157],"Wikipedia":[161,197],"sites":[168],"browser.":[172],"general":[176],"often":[182],"benign":[183],"(for":[184],"example,":[185],"templates),":[186],"but":[187],"6\u201311%":[188],"are":[189,199],"commercial":[190],"possibly":[192],"commercial.":[193],"Most":[194],"(86%)":[198],"commercialized":[200],"(link":[201],"farming":[202],"advertisements).":[204],"For":[205],"phishing,":[206],"we":[207],"focus":[208],"on":[209,218],"PayPal,":[210],"59%":[212],"PayPal-phish":[214],"even":[215],"without":[216],"taking":[217],"intentional":[219],"cloaking.":[220]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2946113142","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2024-12-09T07:53:47.349132","created_date":"2019-05-29"}