{"id":"https://openalex.org/W4225723741","doi":"https://doi.org/10.1109/tifs.2022.3164212","title":"PhishSim: Aiding Phishing Website Detection With a Feature-Free Tool","display_name":"PhishSim: Aiding Phishing Website Detection With a Feature-Free Tool","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225723741","doi":"https://doi.org/10.1109/tifs.2022.3164212"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2022.3164212","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tifs.2022.3164212","pdf_url":"https://ieeexplore.ieee.org/ielx7/10206/9652463/09745933.pdf","source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/10206/9652463/09745933.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048424671","display_name":"Rizka Purwanto","orcid":"https://orcid.org/0000-0002-6440-9580"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rizka Widyarini Purwanto","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","Cyber Security Cooperative Research Centre, Joondalup, WA, Australia","UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6440-9580","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Cyber Security Cooperative Research Centre, Joondalup, WA, Australia","institution_ids":[]},{"raw_affiliation_string":"UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044617871","display_name":"Arindam Pal","orcid":"https://orcid.org/0000-0001-5710-7464"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Arindam Pal","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","Cyber Security Cooperative Research Centre, Joondalup, WA, Australia","UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia","CSIRO Data61, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5710-7464","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Cyber Security Cooperative Research Centre, Joondalup, WA, Australia","institution_ids":[]},{"raw_affiliation_string":"UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia","institution_ids":[]},{"raw_affiliation_string":"CSIRO Data61, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033143541","display_name":"Alan Blair","orcid":"https://orcid.org/0000-0002-1039-4766"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alan Blair","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015261020","display_name":"Sanjay Jha","orcid":"https://orcid.org/0000-0002-1844-1520"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sanjay Jha","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1844-1520","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"UNSW Institute for Cyber Security (IFCYBER), Campbell, Australia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4719,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.98477227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":null,"first_page":"1497","last_page":"1512"},"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":0.998199999332428,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.996999979019165,"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/phishing","display_name":"Phishing","score":0.9040881395339966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8409109115600586},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.613761842250824},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5223937034606934},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5180256962776184},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5003881454467773},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4913152754306793},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4168713092803955},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41463702917099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40370941162109375},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35404717922210693},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.21335908770561218},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15603983402252197},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09151759743690491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09039434790611267}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9040881395339966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409109115600586},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.613761842250824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5223937034606934},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5180256962776184},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5003881454467773},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4913152754306793},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4168713092803955},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41463702917099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40370941162109375},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35404717922210693},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.21335908770561218},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15603983402252197},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09151759743690491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09039434790611267},{"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/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":2,"locations":[{"id":"doi:10.1109/tifs.2022.3164212","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tifs.2022.3164212","pdf_url":"https://ieeexplore.ieee.org/ielx7/10206/9652463/09745933.pdf","source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2207.10801","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.10801","pdf_url":"https://arxiv.org/pdf/2207.10801","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/tifs.2022.3164212","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tifs.2022.3164212","pdf_url":"https://ieeexplore.ieee.org/ielx7/10206/9652463/09745933.pdf","source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320965","display_name":"University of New South Wales","ror":"https://ror.org/03r8z3t63"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225723741.pdf","grobid_xml":"https://content.openalex.org/works/W4225723741.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1851403712","https://openalex.org/W1973264045","https://openalex.org/W1990188874","https://openalex.org/W2025635041","https://openalex.org/W2028223155","https://openalex.org/W2029591949","https://openalex.org/W2121430617","https://openalex.org/W2121990650","https://openalex.org/W2128859735","https://openalex.org/W2139565456","https://openalex.org/W2142995284","https://openalex.org/W2144221002","https://openalex.org/W2154586245","https://openalex.org/W2158063174","https://openalex.org/W2295731716","https://openalex.org/W2393559257","https://openalex.org/W2604422183","https://openalex.org/W2606751384","https://openalex.org/W2755914852","https://openalex.org/W2783674026","https://openalex.org/W2904027722","https://openalex.org/W2962940036","https://openalex.org/W2964636835","https://openalex.org/W2969671680","https://openalex.org/W2971561269","https://openalex.org/W2978628345","https://openalex.org/W3041247367","https://openalex.org/W3047885262","https://openalex.org/W3106126975","https://openalex.org/W6696870837","https://openalex.org/W6753153400","https://openalex.org/W6766395966"],"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":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,18,47,94,110,126,146,157,189],"feature-free":[6],"method":[7,54,131],"for":[8,112],"detecting":[9,137],"phishing":[10,66,82,97,138],"websites":[11,28],"using":[12],"the":[13,24,34,56,75,102,170,178],"Normalized":[14],"Compression":[15],"Distance":[16],"(NCD),":[17],"parameter-free":[19],"similarity":[20,25,63],"measure":[21],"which":[22],"computes":[23,61],"of":[26,50,58,93,96,104,144,152,163,192],"two":[27],"by":[29],"compressing":[30],"them,":[31],"thus":[32],"eliminating":[33,169],"need":[35,171],"to":[36,70,80,87,172,183],"perform":[37,81],"any":[38,44],"feature":[39],"extraction.":[40],"It":[41],"also":[42,100],"removes":[43],"dependence":[45],"on":[46],"specific":[48],"set":[49],"website":[51],"features.":[52],"This":[53],"examines":[55],"HTML":[57],"webpages":[59],"and":[60,114,180],"their":[62],"with":[64,140,188],"known":[65],"websites,":[67,139],"in":[68,85,136,177,185],"order":[69,86],"classify":[71],"them.":[72],"We":[73,99],"use":[74,103],"Furthest":[76],"Point":[77],"First":[78],"algorithm":[79,108],"prototype":[83],"extractions,":[84],"select":[88],"instances":[89],"that":[90],"are":[91],"representative":[92],"cluster":[95],"webpages.":[98],"introduce":[101],"an":[105,141],"incremental":[106],"learning":[107],"as":[109],"framework":[111],"continuous":[113],"adaptive":[115],"detection":[116],"without":[117],"extracting":[118],"new":[119],"features":[120],"when":[121],"concept":[122],"drift":[123],"occurs.":[124],"On":[125],"large":[127],"dataset,":[128],"our":[129],"proposed":[130],"significantly":[132],"outperforms":[133],"previous":[134],"methods":[135],"AUC":[142],"score":[143],"98.68%,":[145],"high":[147],"true":[148],"positive":[149,160],"rate":[150,161],"(TPR)":[151],"around":[153],"90%,":[154],"while":[155],"maintaining":[156],"low":[158],"false":[159],"(FPR)":[162],"0.58%.":[164],"Our":[165],"approach":[166],"uses":[167],"prototypes,":[168],"retain":[173],"long":[174],"term":[175],"data":[176],"future,":[179],"is":[181],"feasible":[182],"deploy":[184],"real":[186],"systems":[187],"processing":[190],"time":[191],"roughly":[193],"0.3":[194],"seconds.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
