{"id":"https://openalex.org/W3118416455","doi":"https://doi.org/10.1145/3444370.3444552","title":"Webpage visual feature extraction and similarity algorithm","display_name":"Webpage visual feature extraction and similarity algorithm","publication_year":2020,"publication_date":"2020-12-04","ids":{"openalex":"https://openalex.org/W3118416455","doi":"https://doi.org/10.1145/3444370.3444552","mag":"3118416455"},"language":"en","primary_location":{"id":"doi:10.1145/3444370.3444552","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444370.3444552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100416932","display_name":"Jingwei Li","orcid":"https://orcid.org/0000-0002-2508-4859"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Li","raw_affiliation_strings":["School of Computer Science and Technolgy, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technolgy, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072540013","display_name":"Xiangzhan Yu","orcid":"https://orcid.org/0000-0002-1183-2844"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangzhan Yu","raw_affiliation_strings":["School of Computer Science and Technolgy, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technolgy, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9872000217437744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7738732099533081},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6361211538314819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5641111135482788},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5633235573768616},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5522829294204712},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5504136085510254},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5475231409072876},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4678384065628052},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.4647578001022339},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3897154927253723},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36264073848724365},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2571909427642822},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15172341465950012},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11899763345718384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738732099533081},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6361211538314819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641111135482788},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5633235573768616},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5522829294204712},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5504136085510254},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5475231409072876},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4678384065628052},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.4647578001022339},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3897154927253723},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36264073848724365},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2571909427642822},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15172341465950012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11899763345718384},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3444370.3444552","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444370.3444552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1803802947","https://openalex.org/W1968197683","https://openalex.org/W1970026646","https://openalex.org/W1975009259","https://openalex.org/W1997657677","https://openalex.org/W2142995284","https://openalex.org/W2980048904"],"related_works":["https://openalex.org/W2149202530","https://openalex.org/W2807822918","https://openalex.org/W2921723332","https://openalex.org/W2482950156","https://openalex.org/W4396966040","https://openalex.org/W2305322260","https://openalex.org/W3139248031","https://openalex.org/W3042334625","https://openalex.org/W4200017362","https://openalex.org/W4388020458"],"abstract_inverted_index":{"Nowadays,":[0],"the":[1,7,27,40,64,70,75,80,85,89,97,102,119,128,135,138,143,146,156,174,177],"Internet":[2],"is":[3,131],"developing":[4],"rapidly,":[5],"and":[6,26,58,78,106,122,150,169,179],"types":[8],"of":[9,42,88,127,137,145,166,176],"websites":[10,32,38],"are":[11,33],"more":[12,21,35],"abundant":[13],"than":[14],"in":[15],"previous":[16],"decades.":[17],"However,":[18],"people":[19],"face":[20],"significant":[22],"network":[23],"security":[24],"risks,":[25],"losses":[28],"caused":[29],"by":[30,92],"phishing":[31,48,167],"even":[34],"severe.":[36],"Phishing":[37],"imitate":[39],"interface":[41],"real":[43],"websites.":[44],"For":[45],"better":[46],"identifying":[47],"websites,":[49],"this":[50],"paper":[51],"proposes":[52],"a":[53,59,110],"visual":[54,60,65,81,90,98,103,129,139,147,151,159],"feature":[55,66,87],"extraction":[56,67],"method":[57,68,114],"similarity":[61,99,136,144,149],"algorithm.":[62],"First,":[63],"improves":[69],"VIPS":[71],"algorithm":[72,100,178],"to":[73,108,118,133,154,172],"extract":[74],"logo":[76],"block":[77,91,152],"calculate":[79,134],"block's":[82],"signature":[83],"as":[84],"image":[86],"perceptual":[93],"hash":[94],"technology.":[95],"Then,":[96],"uses":[101],"blocks'":[104],"coordinates":[105],"thresholds":[107],"find":[109],"one-to-one":[111],"correspondence.":[112],"This":[113],"assigns":[115],"weights":[116],"according":[117],"tree":[120],"structure":[121],"logo.":[123],"The":[124],"Hamming":[125],"distance":[126],"features":[130],"measured":[132],"blocks.":[140],"It":[141],"integrates":[142],"blocks":[148],"weight":[153],"get":[155],"web":[157],"pages'":[158],"similarity.":[160],"Finally,":[161],"we":[162],"use":[163],"multiple":[164],"pairs":[165],"webpages":[168,171],"legitimate":[170],"verify":[173],"feasibility":[175],"achieve":[180],"excellent":[181],"results.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
