{"id":"https://openalex.org/W4308121386","doi":"https://doi.org/10.3390/digital2040027","title":"Significance of Machine Learning for Detection of Malicious Websites on an Unbalanced Dataset","display_name":"Significance of Machine Learning for Detection of Malicious Websites on an Unbalanced Dataset","publication_year":2022,"publication_date":"2022-10-31","ids":{"openalex":"https://openalex.org/W4308121386","doi":"https://doi.org/10.3390/digital2040027"},"language":"en","primary_location":{"id":"doi:10.3390/digital2040027","is_oa":true,"landing_page_url":"https://doi.org/10.3390/digital2040027","pdf_url":"https://www.mdpi.com/2673-6470/2/4/27/pdf?version=1667195540","source":{"id":"https://openalex.org/S4210185390","display_name":"Digital","issn_l":"2673-6470","issn":["2673-6470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mdpi.com/2673-6470/2/4/27/pdf?version=1667195540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060211587","display_name":"Ietezaz Ul Hassan","orcid":null},"institutions":[{"id":"https://openalex.org/I5400463","display_name":"Ghulam Ishaq Khan Institute of Engineering Sciences and Technology","ror":"https://ror.org/01sb6ek09","country_code":"PK","type":"education","lineage":["https://openalex.org/I5400463"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ietezaz Ul Hassan","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan","institution_ids":["https://openalex.org/I5400463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083008291","display_name":"Raja Hashim Ali","orcid":"https://orcid.org/0000-0002-9068-2337"},"institutions":[{"id":"https://openalex.org/I5400463","display_name":"Ghulam Ishaq Khan Institute of Engineering Sciences and Technology","ror":"https://ror.org/01sb6ek09","country_code":"PK","type":"education","lineage":["https://openalex.org/I5400463"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Raja Hashim Ali","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan","institution_ids":["https://openalex.org/I5400463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052772923","display_name":"Zain ul Abideen","orcid":"https://orcid.org/0000-0001-9909-2061"},"institutions":[{"id":"https://openalex.org/I5400463","display_name":"Ghulam Ishaq Khan Institute of Engineering Sciences and Technology","ror":"https://ror.org/01sb6ek09","country_code":"PK","type":"education","lineage":["https://openalex.org/I5400463"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Zain Ul Abideen","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan"],"raw_orcid":"https://orcid.org/0000-0001-9909-2061","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan","institution_ids":["https://openalex.org/I5400463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638829","display_name":"Talha Ali Khan","orcid":"https://orcid.org/0000-0003-3874-4075"},"institutions":[{"id":"https://openalex.org/I2800638415","display_name":"University of Applied Sciences Potsdam","ror":"https://ror.org/012m9bp23","country_code":"DE","type":"education","lineage":["https://openalex.org/I2800638415"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Talha Ali Khan","raw_affiliation_strings":["Faculty of Tech and Software Engineering, University of Europe of Applied Sciences, 14469 Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Tech and Software Engineering, University of Europe of Applied Sciences, 14469 Potsdam, Germany","institution_ids":["https://openalex.org/I2800638415"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079829353","display_name":"Rand Kouatly","orcid":"https://orcid.org/0000-0001-5405-3990"},"institutions":[{"id":"https://openalex.org/I2800638415","display_name":"University of Applied Sciences Potsdam","ror":"https://ror.org/012m9bp23","country_code":"DE","type":"education","lineage":["https://openalex.org/I2800638415"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rand Kouatly","raw_affiliation_strings":["Faculty of Tech and Software Engineering, University of Europe of Applied Sciences, 14469 Potsdam, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5405-3990","affiliations":[{"raw_affiliation_string":"Faculty of Tech and Software Engineering, University of Europe of Applied Sciences, 14469 Potsdam, Germany","institution_ids":["https://openalex.org/I2800638415"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083008291","https://openalex.org/A5100638829"],"corresponding_institution_ids":["https://openalex.org/I2800638415","https://openalex.org/I5400463"],"apc_list":null,"apc_paid":null,"fwci":19.4481,"has_fulltext":true,"cited_by_count":66,"citation_normalized_percentile":{"value":0.99357717,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"4","first_page":"501","last_page":"519"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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/undersampling","display_name":"Undersampling","score":0.8690281510353088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8075170516967773},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.768005907535553},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7309051752090454},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6997441053390503},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6714223623275757},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6155456304550171},{"id":"https://openalex.org/keywords/login","display_name":"Login","score":0.5897627472877502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5747187733650208},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3917047083377838},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.23701566457748413}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.8690281510353088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075170516967773},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.768005907535553},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7309051752090454},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6997441053390503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6714223623275757},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6155456304550171},{"id":"https://openalex.org/C113324615","wikidata":"https://www.wikidata.org/wiki/Q472302","display_name":"Login","level":2,"score":0.5897627472877502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5747187733650208},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3917047083377838},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.23701566457748413},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/digital2040027","is_oa":true,"landing_page_url":"https://doi.org/10.3390/digital2040027","pdf_url":"https://www.mdpi.com/2673-6470/2/4/27/pdf?version=1667195540","source":{"id":"https://openalex.org/S4210185390","display_name":"Digital","issn_l":"2673-6470","issn":["2673-6470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital","raw_type":"journal-article"},{"id":"pmh:oai:mdpi.com:/2673-6470/2/4/27/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/digital2040027","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Digital; Volume 2; Issue 4; Pages: 501-519","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/digital2040027","is_oa":true,"landing_page_url":"https://doi.org/10.3390/digital2040027","pdf_url":"https://www.mdpi.com/2673-6470/2/4/27/pdf?version=1667195540","source":{"id":"https://openalex.org/S4210185390","display_name":"Digital","issn_l":"2673-6470","issn":["2673-6470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308121386.pdf","grobid_xml":"https://content.openalex.org/works/W4308121386.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2077442291","https://openalex.org/W2330219538","https://openalex.org/W2414538037","https://openalex.org/W2590489721","https://openalex.org/W2772362066","https://openalex.org/W2791078573","https://openalex.org/W2802000585","https://openalex.org/W2860801896","https://openalex.org/W2884486887","https://openalex.org/W2899428374","https://openalex.org/W2904800847","https://openalex.org/W2913997948","https://openalex.org/W2979354191","https://openalex.org/W2988668989","https://openalex.org/W2998567488","https://openalex.org/W2999357838","https://openalex.org/W3012062562","https://openalex.org/W3017193407","https://openalex.org/W3022217540","https://openalex.org/W3023211159","https://openalex.org/W3026353565","https://openalex.org/W3033915435","https://openalex.org/W3039276560","https://openalex.org/W3081611791","https://openalex.org/W3098996042","https://openalex.org/W3148181069","https://openalex.org/W3151417188","https://openalex.org/W3194419036","https://openalex.org/W3204452949","https://openalex.org/W3209082359","https://openalex.org/W3217186564","https://openalex.org/W4243367342","https://openalex.org/W4281884841","https://openalex.org/W4288610071","https://openalex.org/W6751448385","https://openalex.org/W6782985868","https://openalex.org/W7045822651"],"related_works":["https://openalex.org/W32988189","https://openalex.org/W4308469503","https://openalex.org/W2904737874","https://openalex.org/W80466363","https://openalex.org/W4389233021","https://openalex.org/W2399571531","https://openalex.org/W2947132063","https://openalex.org/W4390415670","https://openalex.org/W4288337828","https://openalex.org/W4287816717"],"abstract_inverted_index":{"It":[0],"is":[1],"hard":[2],"to":[3,52,102,121],"trust":[4],"any":[5],"data":[6,19,150],"entry":[7],"on":[8,58],"online":[9],"websites":[10,13,79],"as":[11,80,109],"some":[12],"may":[14],"be":[15,34],"malicious,":[16],"and":[17,29,54,66,77,84,98,115,157,165,196],"gather":[18],"for":[20,36,90,153,161,193],"illegal":[21],"or":[22],"unintended":[23],"use.":[24],"For":[25],"example,":[26,91,154],"bank":[27],"login":[28],"credit":[30],"card":[31],"information":[32],"can":[33],"misused":[35],"financial":[37],"theft.":[38],"To":[39],"make":[40],"users":[41],"aware":[42],"of":[43,47,62,64,73,125,147],"the":[44,56,71,123,130,134,163,167,175,177,182,186,194],"digital":[45],"safety":[46],"websites,":[48],"we":[49],"have":[50],"tried":[51],"identify":[53],"learn":[55],"pattern":[57],"a":[59,81,139,144],"dataset":[60,131,164],"consisting":[61],"features":[63],"malicious":[65,76,197],"benign":[67,78,195],"websites.":[68,148],"We":[69],"treated":[70],"problem":[72,83],"differentiation":[74],"between":[75],"classification":[82,127],"applied":[85,160],"several":[86],"machine":[87,135],"learning":[88,136],"techniques,":[89,152],"random":[92,178],"forest,":[93],"decision":[94],"tree,":[95],"logistic":[96],"regression,":[97],"support":[99],"vector":[100],"machines":[101],"this":[103],"data.":[104],"Several":[105],"evaluation":[106,191],"metrics":[107,192],"such":[108],"accuracy,":[110],"precision,":[111],"recall,":[112],"F1":[113],"score,":[114],"false":[116],"positive":[117],"rate,":[118],"were":[119,159],"used":[120],"evaluate":[122],"performance":[124],"each":[126],"technique.":[128],"Since":[129],"was":[132],"imbalanced,":[133],"models":[137],"developed":[138],"bias":[140],"during":[141],"training":[142],"toward":[143],"specific":[145],"class":[146],"Multiple":[149],"balancing":[151,162,174],"undersampling,":[155],"oversampling,":[156],"SMOTE,":[158],"removing":[166],"bias.":[168],"Our":[169],"experiments":[170],"showed":[171,185],"that":[172],"after":[173],"data,":[176],"forest":[179],"algorithm":[180],"using":[181],"oversampling":[183],"technique":[184],"best":[187],"results":[188],"in":[189],"all":[190],"website":[198],"feature":[199],"dataset.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":19}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}
