{"id":"https://openalex.org/W3216950620","doi":"https://doi.org/10.1145/3485983.3494857","title":"Discovering obscure looking glass sites on the web to facilitate internet measurement research","display_name":"Discovering obscure looking glass sites on the web to facilitate internet measurement research","publication_year":2021,"publication_date":"2021-12-02","ids":{"openalex":"https://openalex.org/W3216950620","doi":"https://doi.org/10.1145/3485983.3494857","mag":"3216950620"},"language":"en","primary_location":{"id":"doi:10.1145/3485983.3494857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485983.3494857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on emerging Networking EXperiments and Technologies","raw_type":"proceedings-article"},"type":"article","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/A5026586512","display_name":"Shuying Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuying Zhuang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075088248","display_name":"Jessie Hui Wang","orcid":"https://orcid.org/0000-0002-7825-4137"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jessie Hui Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100660344","display_name":"Jilong Wang","orcid":"https://orcid.org/0000-0002-4493-5145"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jilong Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083860232","display_name":"Zujiang Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zujiang Pan","raw_affiliation_strings":["Tencent Technology"],"affiliations":[{"raw_affiliation_string":"Tencent Technology","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083841001","display_name":"Tianhao Wu","orcid":"https://orcid.org/0000-0001-7465-1242"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Wu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325259","display_name":"Fenghua Li","orcid":"https://orcid.org/0000-0003-0638-5610"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenghua Li","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiyong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Zhang","raw_affiliation_strings":["CETCSC"],"affiliations":[{"raw_affiliation_string":"CETCSC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5026586512"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.1304,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92866586,"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":"426","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9980999827384949,"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":0.994700014591217,"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/web-crawler","display_name":"Web crawler","score":0.952980637550354},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7555249929428101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7197750210762024},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6232734322547913},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5812041759490967},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5550932884216309},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5363437533378601},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.49682286381721497},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4856456518173218},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4631724953651428},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.4510577917098999},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4116055369377136},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3901347517967224},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.2733858823776245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2599797248840332},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.15239346027374268}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.952980637550354},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7555249929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197750210762024},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6232734322547913},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5812041759490967},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5550932884216309},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5363437533378601},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.49682286381721497},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4856456518173218},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4631724953651428},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.4510577917098999},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4116055369377136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3901347517967224},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.2733858823776245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2599797248840332},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.15239346027374268},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485983.3494857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485983.3494857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on emerging Networking EXperiments and Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1481372933","https://openalex.org/W1493526108","https://openalex.org/W1900476884","https://openalex.org/W1916662222","https://openalex.org/W1978033244","https://openalex.org/W1990500986","https://openalex.org/W2014134732","https://openalex.org/W2039161780","https://openalex.org/W2044744030","https://openalex.org/W2050871273","https://openalex.org/W2092233407","https://openalex.org/W2102475112","https://openalex.org/W2103117727","https://openalex.org/W2118437126","https://openalex.org/W2123958887","https://openalex.org/W2166559705","https://openalex.org/W2168947441","https://openalex.org/W2177585230","https://openalex.org/W2295430786","https://openalex.org/W2358081021","https://openalex.org/W2416687618","https://openalex.org/W2553660799","https://openalex.org/W2571327869","https://openalex.org/W2619095830","https://openalex.org/W2620616291","https://openalex.org/W2750391883","https://openalex.org/W2766883061","https://openalex.org/W2803480040","https://openalex.org/W2900101584","https://openalex.org/W2917016699","https://openalex.org/W2950597530","https://openalex.org/W2951936613","https://openalex.org/W2978983562","https://openalex.org/W3003479855","https://openalex.org/W3022882875","https://openalex.org/W3094353319","https://openalex.org/W3094518463","https://openalex.org/W4206668729","https://openalex.org/W4230638559","https://openalex.org/W4288086151","https://openalex.org/W4289038676"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2183593492","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W2389761961","https://openalex.org/W4254300012","https://openalex.org/W1999548128","https://openalex.org/W2378232036","https://openalex.org/W2794831687","https://openalex.org/W4313495655"],"abstract_inverted_index":{"Despite":[0],"researchers":[1],"have":[2],"noticed":[3],"that":[4,40,98],"Looking":[5],"Glass":[6],"(LG)":[7],"vantage":[8],"points":[9],"(VPs)":[10],"are":[11,41,53,155,246],"valuable":[12],"for":[13],"Internet":[14,232],"measurement":[15,250],"researches,":[16],"they":[17],"can":[18,81,190],"only":[19],"exploit":[20],"VPs":[21,197,209,219],"from":[22,198],"well-known":[23],"LG":[24,29,38,50,76,113,118,134,165,196,208],"sites":[25,39,77,114,166],"published":[26,43],"on":[27,86,131,167],"several":[28],"portal":[30,46],"pages.":[31,89,119],"There":[32],"should":[33],"be":[34,57],"a":[35,95,125,143,160,235],"lot":[36,144],"of":[37,145,175,217,230],"not":[42,54],"in":[44,226],"these":[45],"pages,":[47],"namely":[48],"obscure":[49,164,194],"sites,":[51],"which":[52,80,189],"easy":[55],"to":[56,72,115,136,158,162,248],"found":[58],"and":[59,104,214,220,241],"exploited":[60],"by":[61,111,234],"researchers.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,152,154,183,221],"design":[67],"an":[68,186],"efficient":[69],"focused":[70,92,122,177,204],"crawler":[71,93,123],"discover":[73,116,163],"as":[74,78,151],"many":[75],"possible":[79],"avoid":[82],"unnecessary":[83,146],"resource":[84,147],"consumption":[85],"analyzing":[87],"irrelevant":[88,139],"Our":[90,239],"designed":[91],"takes":[94,124],"similarity-guided":[96],"search":[97,102],"exploits":[99],"the":[100,107,121,156,168,173,212,228,242,249],"well-developed":[101],"engines":[103],"comprehensively":[105],"mines":[106],"common":[108],"features":[109,135],"shared":[110],"known":[112],"more":[117],"Moreover,":[120],"two-step":[126],"PU":[127],"learning":[128],"classifier":[129],"based":[130],"carefully":[132],"selected":[133],"efficiently":[137],"discard":[138],"URLs,":[140],"thus":[141],"avoiding":[142],"consumption.":[148],"As":[149],"far":[150],"know,":[153],"first":[157],"develop":[159,185],"method":[161,240],"web.":[169],"Experimental":[170],"results":[171],"show":[172,222],"effectiveness":[174],"our":[176,203],"crawler.":[178,205],"To":[179],"facilitate":[180],"practical":[181],"applications,":[182],"further":[184],"automation":[187],"tool,":[188],"successfully":[191],"retrieve":[192],"910":[193,207],"automatable":[195],"relevant":[199],"pages":[200],"obtained":[201],"through":[202],"The":[206],"significantly":[210],"increase":[211],"geographic":[213],"network":[215],"coverage":[216],"available":[218],"their":[223],"potential":[224],"values":[225],"improving":[227],"completeness":[229],"AS-level":[231],"topology":[233],"simple":[236],"case":[237],"study.":[238],"final":[243],"VP":[244],"list":[245],"beneficial":[247],"community.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
