{"id":"https://openalex.org/W4313015228","doi":"https://doi.org/10.1109/dsit55514.2022.9943832","title":"On Phishing: URL Lexical and Network Traffic Features Analysis and Knowledge Extraction using Machine Learning Algorithms (A Comparison Study)","display_name":"On Phishing: URL Lexical and Network Traffic Features Analysis and Knowledge Extraction using Machine Learning Algorithms (A Comparison Study)","publication_year":2022,"publication_date":"2022-07-22","ids":{"openalex":"https://openalex.org/W4313015228","doi":"https://doi.org/10.1109/dsit55514.2022.9943832"},"language":"en","primary_location":{"id":"doi:10.1109/dsit55514.2022.9943832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsit55514.2022.9943832","pdf_url":null,"source":{"id":"https://openalex.org/S4363608293","display_name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","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/A5008089330","display_name":"Wesam Fadheel","orcid":null},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wesam Fadheel","raw_affiliation_strings":["Western Michigan University,Department of Computer Science,Kalamazoo,USA,MI 49008"],"affiliations":[{"raw_affiliation_string":"Western Michigan University,Department of Computer Science,Kalamazoo,USA,MI 49008","institution_ids":["https://openalex.org/I141649380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014692416","display_name":"Wassnaa Al-Mawee","orcid":"https://orcid.org/0000-0001-6536-7338"},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wassnaa Al-Mawee","raw_affiliation_strings":["Western Michigan University,Department of Computer Science,Kalamazoo,USA,MI 49008"],"affiliations":[{"raw_affiliation_string":"Western Michigan University,Department of Computer Science,Kalamazoo,USA,MI 49008","institution_ids":["https://openalex.org/I141649380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002599549","display_name":"Steve Carr","orcid":"https://orcid.org/0000-0002-8922-0805"},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Carr","raw_affiliation_strings":["Western Michigan University,Department of Computer Science,Kalamazoo,USA,MI 49008"],"affiliations":[{"raw_affiliation_string":"Western Michigan University,Department of Computer Science,Kalamazoo,USA,MI 49008","institution_ids":["https://openalex.org/I141649380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008089330"],"corresponding_institution_ids":["https://openalex.org/I141649380"],"apc_list":null,"apc_paid":null,"fwci":0.4372,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63326566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"7"},"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":0.9969000220298767,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8440927863121033},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.8040081262588501},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6564472913742065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5988041758537292},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.5379868745803833},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.49408915638923645},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4754321575164795},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.47241201996803284},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.4670388102531433},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39372187852859497},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.19841870665550232},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08110418915748596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440927863121033},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.8040081262588501},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6564472913742065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5988041758537292},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.5379868745803833},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.49408915638923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4754321575164795},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.47241201996803284},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4670388102531433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39372187852859497},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.19841870665550232},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08110418915748596},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsit55514.2022.9943832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsit55514.2022.9943832","pdf_url":null,"source":{"id":"https://openalex.org/S4363608293","display_name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2184870664","https://openalex.org/W2245177186","https://openalex.org/W2521519773","https://openalex.org/W2795183095","https://openalex.org/W2998448592","https://openalex.org/W3034568539","https://openalex.org/W3171018146","https://openalex.org/W3171990258","https://openalex.org/W6750031092","https://openalex.org/W6995772189"],"related_works":["https://openalex.org/W3118827657","https://openalex.org/W3191249021","https://openalex.org/W2345184372","https://openalex.org/W3098409150","https://openalex.org/W4321505170","https://openalex.org/W3195168932","https://openalex.org/W1996541855","https://openalex.org/W3210918776","https://openalex.org/W4225292389","https://openalex.org/W4293525103"],"abstract_inverted_index":{"Phishing":[0],"is":[1,77],"a":[2,7,78,85,90,149,156,257,272],"criminal":[3],"act":[4],"in":[5,262],"which":[6,159],"Phisher":[8],"creates":[9],"almost":[10],"identical":[11],"website":[12],"connections":[13],"exploiting":[14],"URL":[15,61,93,112,127,282],"Lexical":[16,110,128,218,225,283],"characteristics":[17],"to":[18,38,49,58,99,133],"dupe":[19],"unsuspecting":[20],"users":[21],"into":[22],"exposing":[23],"sensitive":[24],"information":[25],"such":[26],"as":[27,148,155],"financial":[28],"data,":[29],"address,":[30],"and":[31,69,83,95,101,122,129,153,165,169,188,193,207,211,233,237,270,277,284],"other":[32],"personal":[33],"information.":[34],"Phishers":[35],"recently":[36],"sought":[37],"trick":[39],"security":[40],"experts":[41],"by":[42,162,171],"masking":[43],"malicious":[44,103,135,279],"URLs":[45,104,280],"with":[46,264],"obfuscation":[47],"techniques":[48,72],"make":[50],"them":[51],"appear":[52],"legitimate.":[53],"This":[54,75],"action":[55],"leads":[56],"us":[57],"conclude":[59],"that":[60,88,275],"lexical":[62],"features":[63,98,132,150,180,219,226,253],"analysis":[64,71],"approaches":[65],"are":[66,73,142,160,260],"absolute":[67],"procedures,":[68],"extract":[70],"required.":[74],"research":[76],"first":[79],"step":[80,267],"toward":[81],"designing":[82,269],"developing":[84,271],"decision-making":[86,273],"system":[87],"uses":[89],"combination":[91],"of":[92,126,217,250,268],"Lexical,":[94],"Network":[96,113,130,178,251,285],"Traffic":[97,114,131,252,286],"detect":[100,134],"classify":[102],"rather":[105],"than":[106],"relying":[107],"solely":[108],"on":[109],"or":[111],"features.":[115,287],"To":[116],"achieve":[117],"our":[118],"goal,":[119],"we":[120,259],"examined":[121],"assessed":[123],"the":[124,138,172,183,215,229,248,265],"usage":[125],"URLs.":[136],"In":[137,222],"study,":[139],"three":[140],"methodologies":[141],"used:":[143],"Complete":[144],"Features,":[145],"KMO":[146,197,230],"test":[147],"selection":[151],"method,":[152,158],"PCA":[154,204,241],"dimensionality":[157],"tested":[161],"LR,":[163,186],"SVM,":[164,187],"KNN":[166,189,234,243],"classification":[167],"algorithms":[168],"evaluated":[170],"Confusion":[173],"Matrix":[174],"Accuracy":[175],"measure.":[176],"Using":[177],"Traffics":[179],"(ISCXURL":[181,254],"dataset),":[182,228],"W/O":[184],"approach:":[185,198,205,231,242],"has":[190,200,235,244],"92%,":[191],"94%,":[192],"93%":[194],"accuracy.":[195,202,239],"The":[196,203,240],"SVM":[199,208],"91%":[201],"LR":[206,232],"have":[209],"92%":[210],"94%":[212,238],"accuracy,":[213,246],"surpassing":[214,247],"use":[216,249],"(UCI":[220,227],"dataset).":[221,255],"contrast,":[223],"using":[224],"90%":[236],"95%":[245],"As":[256],"result,":[258],"confident":[261],"proceeding":[263],"next":[266],"application":[274],"detects":[276],"classifies":[278],"utilizing":[281]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
