{"id":"https://openalex.org/W3202507231","doi":"https://doi.org/10.1109/case49439.2021.9551622","title":"An Unsupervised-Learning Based Method for Detecting Groups of Malicious Web Crawlers in Internet","display_name":"An Unsupervised-Learning Based Method for Detecting Groups of Malicious Web Crawlers in Internet","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3202507231","doi":"https://doi.org/10.1109/case49439.2021.9551622","mag":"3202507231"},"language":"en","primary_location":{"id":"doi:10.1109/case49439.2021.9551622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49439.2021.9551622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","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/A5074077045","display_name":"Tianyi Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyi Yue","raw_affiliation_strings":["MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065675742","display_name":"Yadong Zhou","orcid":"https://orcid.org/0000-0003-0345-3518"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Zhou","raw_affiliation_strings":["MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101996884","display_name":"Bowen Hu","orcid":"https://orcid.org/0000-0003-3829-1563"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Hu","raw_affiliation_strings":["MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067277859","display_name":"Zhanbo Xu","orcid":"https://orcid.org/0000-0002-8364-0753"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanbo Xu","raw_affiliation_strings":["MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"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":"Xiaohong Guan","raw_affiliation_strings":["Department of Automation, Center for Intelligent and Networked Systems (CFINS), TNLIST, Tsinghua University, Beijing, China","MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), TNLIST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029175864","display_name":"Hao Zhou","orcid":"https://orcid.org/0000-0002-0717-6784"},"institutions":[{"id":"https://openalex.org/I4399598487","display_name":"River Security Inc. (China)","ror":"https://ror.org/04b8jtz89","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["River Security Information Technology (Shanghai) Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"River Security Information Technology (Shanghai) Co., Ltd., China","institution_ids":["https://openalex.org/I4399598487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101733605","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-0389-2553"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5074077045"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.2754,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62947193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"367","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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":0.9972000122070312,"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":0.8794056177139282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952333688735962},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6147866249084473},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5799906253814697},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5555746555328369},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.5326781868934631},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5021131038665771},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4568827748298645},{"id":"https://openalex.org/keywords/internet-security","display_name":"Internet security","score":0.44544944167137146},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42693933844566345},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37095367908477783},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3426976203918457},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25314199924468994},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.21036884188652039},{"id":"https://openalex.org/keywords/information-security","display_name":"Information security","score":0.18381300568580627}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8794056177139282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952333688735962},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6147866249084473},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5799906253814697},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5555746555328369},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.5326781868934631},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5021131038665771},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4568827748298645},{"id":"https://openalex.org/C22111027","wikidata":"https://www.wikidata.org/wiki/Q1070427","display_name":"Internet security","level":4,"score":0.44544944167137146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42693933844566345},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37095367908477783},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3426976203918457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25314199924468994},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.21036884188652039},{"id":"https://openalex.org/C527648132","wikidata":"https://www.wikidata.org/wiki/Q189900","display_name":"Information security","level":2,"score":0.18381300568580627},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C29983905","wikidata":"https://www.wikidata.org/wiki/Q7445066","display_name":"Security service","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case49439.2021.9551622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49439.2021.9551622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3135458743","display_name":null,"funder_award_id":"61833015,U1766215,U1736205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3743187628","display_name":null,"funder_award_id":"xzy012019036","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5206708238","display_name":null,"funder_award_id":"2018YFB0803501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W65738273","https://openalex.org/W201974436","https://openalex.org/W1532325895","https://openalex.org/W1673310716","https://openalex.org/W1781642226","https://openalex.org/W2084585486","https://openalex.org/W2121947440","https://openalex.org/W2125070513","https://openalex.org/W2127218421","https://openalex.org/W2408574227","https://openalex.org/W2556283912","https://openalex.org/W2565517508","https://openalex.org/W2784038944","https://openalex.org/W2963062084","https://openalex.org/W3048741687"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2389761961","https://openalex.org/W4254300012","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W1999548128","https://openalex.org/W2102475112","https://openalex.org/W2626999804","https://openalex.org/W4250004941","https://openalex.org/W2097808084"],"abstract_inverted_index":{"Malicious":[0],"web":[1,14,20,25,50,108,138],"crawler":[2,21],"has":[3],"been":[4],"a":[5,64,84,117,141,150],"serious":[6],"threat":[7],"to":[8,91,102],"the":[9,32,61,72,93,104,131],"security":[10],"and":[11,29,79,149],"performance":[12],"of":[13,34,74,106,122,147,156],"servers":[15],"in":[16],"Internet.":[17],"Generally,":[18],"malicious":[19,49,107,137],"systematically":[22],"obtains":[23],"massive":[24],"pages":[26],"without":[27],"approval,":[28],"may":[30],"involve":[31],"theft":[33],"data":[35,119],"assets.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"an":[42],"unsupervised":[43],"learning":[44],"based":[45,115],"method":[46,53,62,112,133],"for":[47,67],"detecting":[48],"crawler.":[51],"The":[52,110],"can":[54,134],"be":[55],"divided":[56],"into":[57,95],"three":[58],"phases.":[59],"Firstly,":[60],"generates":[63],"representative":[65],"vector":[66],"each":[68],"client":[69],"by":[70],"combining":[71],"information":[73],"its":[75],"visiting":[76],"statistic":[77],"behaviors":[78],"page":[80],"request":[81],"stream.":[82],"Secondly,":[83],"new":[85],"subspace":[86],"clustering":[87],"algorithm":[88],"is":[89,113],"developed":[90],"cluster":[92],"clients":[94],"groups.":[96],"Finally,":[97],"four":[98],"metrics":[99],"are":[100],"designed":[101],"detect":[103,136],"groups":[105],"crawlers.":[109],"proposed":[111,132],"validated":[114],"on":[116],"real":[118],"set":[120],"consisting":[121],"580":[123],"thousand":[124],"accessing":[125],"requests.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"accurately":[135],"crawlers":[139],"with":[140],"high":[142],"TPR":[143],"(true":[144],"positive":[145,154],"rate)":[146,155],"91.0%":[148],"low":[151],"FPR":[152],"(false":[153],"1.3%.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
