{"id":"https://openalex.org/W3081036431","doi":"https://doi.org/10.1145/3407023.3407035","title":"Machine learning for tree structures in fake site detection","display_name":"Machine learning for tree structures in fake site detection","publication_year":2020,"publication_date":"2020-08-25","ids":{"openalex":"https://openalex.org/W3081036431","doi":"https://doi.org/10.1145/3407023.3407035","mag":"3081036431"},"language":"en","primary_location":{"id":"doi:10.1145/3407023.3407035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3407023.3407035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Availability, Reliability and Security","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/A5012874263","display_name":"Taichi Ishikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taichi Ishikawa","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106730954","display_name":"Yulu Liu","orcid":"https://orcid.org/0000-0002-0496-8962"},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu-Lu Liu","raw_affiliation_strings":["Rakuten, Inc, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten, Inc, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029804415","display_name":"David Shepard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099074","display_name":"Evidation Health (United States)","ror":"https://ror.org/00vhpak23","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Lawrence Shepard","raw_affiliation_strings":["Evidation Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Evidation Health","institution_ids":["https://openalex.org/I4210099074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039423670","display_name":"Kilho Shin","orcid":"https://orcid.org/0000-0002-0425-8485"},"institutions":[{"id":"https://openalex.org/I45391821","display_name":"Gakushuin University","ror":"https://ror.org/037s2db26","country_code":"JP","type":"education","lineage":["https://openalex.org/I45391821"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kilho Shin","raw_affiliation_strings":["Gakushuin University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gakushuin University, Japan","institution_ids":["https://openalex.org/I45391821"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1139,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84485837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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":1.0,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7382479906082153},{"id":"https://openalex.org/keywords/tree-kernel","display_name":"Tree kernel","score":0.6657363772392273},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6527601480484009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6160167455673218},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5193454027175903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5055584907531738},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4900463819503784},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.48899781703948975},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.48080793023109436},{"id":"https://openalex.org/keywords/kernel-principal-component-analysis","display_name":"Kernel principal component analysis","score":0.4622056484222412},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.45920851826667786},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4260435998439789},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.35747334361076355},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.15242239832878113},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14643362164497375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08235505223274231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382479906082153},{"id":"https://openalex.org/C140417398","wikidata":"https://www.wikidata.org/wiki/Q16933942","display_name":"Tree kernel","level":5,"score":0.6657363772392273},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6527601480484009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6160167455673218},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5193454027175903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055584907531738},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4900463819503784},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.48899781703948975},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.48080793023109436},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.4622056484222412},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.45920851826667786},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4260435998439789},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.35747334361076355},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.15242239832878113},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14643362164497375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08235505223274231},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3407023.3407035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3407023.3407035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Availability, Reliability and Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W179694669","https://openalex.org/W1647671624","https://openalex.org/W1988068423","https://openalex.org/W2003219686","https://openalex.org/W2021088858","https://openalex.org/W2036714085","https://openalex.org/W2040750298","https://openalex.org/W2046953300","https://openalex.org/W2163509192","https://openalex.org/W2174789775","https://openalex.org/W2190286163","https://openalex.org/W2531819622","https://openalex.org/W2582397176","https://openalex.org/W2963792772","https://openalex.org/W2997546679","https://openalex.org/W3184928437"],"related_works":["https://openalex.org/W2001772920","https://openalex.org/W2512565647","https://openalex.org/W2027376491","https://openalex.org/W2071590642","https://openalex.org/W1984421104","https://openalex.org/W3013206934","https://openalex.org/W2393746448","https://openalex.org/W2366185040","https://openalex.org/W2182834820","https://openalex.org/W2398887903"],"abstract_inverted_index":{"Tree":[0],"data":[1,40,57,70,107],"analysis":[2,20,41,58,121],"has":[3,67,85,185],"many":[4],"applications":[5],"in":[6,59,90,135],"information":[7],"security.":[8],"In":[9,231],"particular,":[10],"HTML":[11],"pages'":[12],"DOM":[13,300,322],"trees":[14],"are":[15,133],"an":[16,162,232],"important":[17],"target":[18],"of":[19,52,74,119,176,206,215,222,238],"because":[21],"web":[22],"pages":[23],"can":[24,158],"be":[25,159],"vectors":[26,73],"for,":[27],"and":[28,110,126,153,291,308],"targets":[29],"of,":[30],"major":[31,244],"cyberattacks":[32],"like":[33,77],"phishing.":[34],"Previous":[35],"attempts":[36],"to":[37,128,168,173,212,298,327],"incorporate":[38],"tree":[39,56,91,178],"into":[42],"security":[43,65,200],"applications,":[44],"however,":[45,84],"have":[46],"been":[47,186],"hampered":[48],"by":[49,242],"the":[50,103,137,144,169,204,213,275,296],"lack":[51],"efficient":[53],"methods":[54,114,284],"for":[55,198],"machine":[60,79],"learning.":[61],"As":[62],"such,":[63],"most":[64,78,177],"research":[66],"focused":[68],"on":[69,234,286],"representable":[71],"as":[72,124,251,253,259,261],"real":[75,236],"numbers,":[76],"learning":[80],"work.":[81],"Recent":[82],"work,":[83],"yielded":[86],"several":[87],"efficiency":[88,266],"break-throughs":[89],"analysis.":[92,112],"One":[93],"example":[94],"is":[95,136,149,267,295],"kernel":[96,142],"methods,":[97],"a":[98,117,194,220,226,235,243,320],"methodological":[99],"bridge":[100],"that":[101],"fills":[102],"gap":[104],"between":[105],"discretely-structured":[106],"(like":[108],"trees)":[109],"multivariate":[111,120],"Kernel":[113],"enable":[115],"applying":[116],"variety":[118],"techniques":[122],"such":[123],"SVM":[125,257],"PCA":[127],"trees.":[129],"The":[130,140],"method":[131,197,248],"we":[132,209],"interested":[134],"subpath":[138,141,195],"kernel.":[139],"offers":[143],"following":[145],"advantages:":[146],"(1)":[147],"it":[148,157,211,304],"invariant":[150],"over":[151],"ordered":[152],"unordered":[154],"trees;":[155],"(2)":[156],"computed":[160],"using":[161],"extremely":[163],"fast":[164],"linear-time":[165],"algorithm":[166],"compared":[167],"quadratic":[170],"time":[171],"required":[172],"compute":[174],"values":[175],"kernels;":[179],"(3)":[180],"its":[181],"excellent":[182],"prediction":[183],"accuracy":[184,250,276],"proven":[187],"through":[188],"intensive":[189],"experiments.":[190],"This":[191],"paper":[192],"proposes":[193],"kernel-based":[196],"tree-structured":[199],"data.":[201],"To":[202],"demonstrate":[203],"effectiveness":[205],"our":[207,247,293],"method,":[208],"apply":[210],"problem":[214],"detecting":[216],"fake":[217,239],"e-commerce":[218,245],"sites,":[219],"sub-problem":[221],"phishing":[223,282],"detection":[224,283],"with":[225,258,270],"significant":[227],"real-world":[228],"financial":[229],"cost.":[230],"experiment":[233],"dataset":[237],"sites":[240],"provided":[241],"company,":[246],"exhibited":[249],"high":[252],"0.998":[254],"when":[255],"training":[256,273],"few":[260],"1,000":[262],"instances.":[263],"Its":[264],"generalization":[265],"also":[268],"excellent:":[269],"only":[271],"100":[272],"instances,":[274],"score":[277],"reaches":[278],"0.996.":[279],"While":[280],"previous":[281],"relied":[285],"textual":[287],"content,":[288],"URL":[289,315],"components,":[290],"blacklists,":[292],"approach":[294],"first":[297],"leverage":[299],"trees,":[301],"which":[302],"makes":[303],"both":[305],"more":[306,309],"effective":[307],"robust":[310],"against":[311],"adversarial":[312],"attacks.":[313],"Unlike":[314],"or":[316],"content":[317],"changes,":[318],"changing":[319],"page's":[321],"structure":[323],"incurs":[324],"large":[325],"costs":[326],"criminals.":[328]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}