{"id":"https://openalex.org/W2743565933","doi":"https://doi.org/10.1109/isi.2017.8004883","title":"Prioritized active learning for malicious URL detection using weighted text-based features","display_name":"Prioritized active learning for malicious URL detection using weighted text-based features","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2743565933","doi":"https://doi.org/10.1109/isi.2017.8004883","mag":"2743565933"},"language":"en","primary_location":{"id":"doi:10.1109/isi.2017.8004883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isi.2017.8004883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Intelligence and Security Informatics (ISI)","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/A5013780049","display_name":"Sreyasee Das Bhattacharjee","orcid":"https://orcid.org/0000-0003-4369-0833"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyasee Das Bhattacharjee","raw_affiliation_strings":["College of Computing and Informatics, University of North Carolina, Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Informatics, University of North Carolina, Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111949314","display_name":"Ashit Talukder","orcid":null},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashit Talukder","raw_affiliation_strings":["College of Computing and Informatics, University of North Carolina, Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Informatics, University of North Carolina, Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043893479","display_name":"Ehab Al\u2010Shaer","orcid":"https://orcid.org/0000-0002-7665-8293"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ehab Al-Shaer","raw_affiliation_strings":["College of Computing and Informatics, University of North Carolina, Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Informatics, University of North Carolina, Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112513206","display_name":"Pratik Doshi","orcid":null},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratik Doshi","raw_affiliation_strings":["College of Computing and Informatics, University of North Carolina, Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Informatics, University of North Carolina, Charlotte","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102149020"],"apc_list":null,"apc_paid":null,"fwci":1.5104,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85717067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"112"},"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":0.9980000257492065,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9977999925613403,"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":0.8719329833984375},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6881936192512512},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6156668066978455},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5554222464561462},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5473806858062744},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5332344174385071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5070314407348633},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.45430123805999756},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4343371093273163},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4134005904197693},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3630027174949646},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.11967569589614868},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10836371779441833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8719329833984375},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6881936192512512},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6156668066978455},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5554222464561462},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5473806858062744},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5332344174385071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070314407348633},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.45430123805999756},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4343371093273163},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4134005904197693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3630027174949646},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.11967569589614868},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10836371779441833},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isi.2017.8004883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isi.2017.8004883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Intelligence and Security Informatics (ISI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W777281333","https://openalex.org/W868043366","https://openalex.org/W1970867218","https://openalex.org/W2006435082","https://openalex.org/W2007223965","https://openalex.org/W2057871674","https://openalex.org/W2066935271","https://openalex.org/W2089635233","https://openalex.org/W2101234009","https://openalex.org/W2140128091","https://openalex.org/W2143043751","https://openalex.org/W2146729596","https://openalex.org/W2149397565","https://openalex.org/W2278186031","https://openalex.org/W2361517492","https://openalex.org/W2553010863","https://openalex.org/W2555759095","https://openalex.org/W2559591242","https://openalex.org/W2951911250","https://openalex.org/W6675354045","https://openalex.org/W6680659571"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2361861616","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W2794071810","https://openalex.org/W61058509"],"abstract_inverted_index":{"Data":[0],"analytics":[1,55],"is":[2,44,71,121,136],"being":[3],"increasingly":[4],"used":[5],"in":[6,14,98,132,173,179],"cyber-security":[7,32,101],"problems,":[8],"and":[9,19,47,74,184],"found":[10],"to":[11,113,156,169,220],"be":[12,221],"useful":[13,194],"cases":[15],"where":[16],"data":[17,38,130,151],"volumes":[18],"heterogeneity":[20],"make":[21],"it":[22],"cumbersome":[23],"for":[24,51,190,207],"manual":[25,73],"assessment":[26],"by":[27,140,244],"security":[28,54],"experts.":[29],"In":[30,82,225],"practical":[31,100],"scenarios":[33],"involving":[34],"data-driven":[35],"analytics,":[36],"obtaining":[37],"with":[39,200,227],"annotations":[40],"(i.e.":[41],"ground-truth":[42],"labels)":[43],"a":[45,76,99,109,115,124,166,180,213],"challenging":[46],"known":[48],"limiting":[49],"factor":[50],"many":[52],"supervised":[53],"task.":[56],"Significant":[57],"portions":[58],"of":[59,69,79,103,127,149,175,216,230],"the":[60,67,128,146,158,176,235,242],"large":[61,147,214],"datasets":[62],"typically":[63],"remain":[64],"unlabelled,":[65],"as":[66,245,247],"task":[68],"annotation":[70],"extensively":[72],"requires":[75],"huge":[77],"amount":[78,126,215],"expert":[80],"intervention.":[81],"this":[83,96],"paper,":[84],"we":[85,107],"propose":[86],"an":[87,133],"effective":[88],"active":[89,201],"learning":[90,182,202],"approach":[91,112],"that":[92,152],"can":[93],"efficiently":[94],"address":[95],"limitation":[97],"problem":[102],"Phishing":[104],"categorization,":[105],"whereby":[106],"use":[108],"human-machine":[110],"collaborative":[111],"design":[114],"semi-supervised":[116],"solution.":[117],"An":[118,193],"initial":[119],"classifier":[120,159],"learnt":[122],"on":[123],"small":[125],"annotated":[129,217],"which":[131],"iterative":[134],"manner,":[135],"then":[137],"gradually":[138],"updated":[139],"shortlisting":[141],"only":[142],"relevant":[143],"samples":[144,219],"from":[145],"pool":[148],"unlabelled":[150],"are":[153],"most":[154],"likely":[155],"influence":[157],"performance":[160,178,206],"fast.":[161],"Prioritized":[162],"Active":[163],"Learning":[164],"shows":[165,203,238],"significant":[167,239],"promise":[168],"achieve":[170],"faster":[171],"convergence":[172],"terms":[174],"classification":[177,205],"batch":[181],"framework,":[183],"thus":[185],"requiring":[186,212],"even":[187],"lesser":[188],"effort":[189],"human":[191],"annotation.":[192],"feature":[195],"weight":[196],"update":[197],"technique":[198],"combined":[199],"promising":[204],"categorizing":[208],"Phishing/malicious":[209],"URLs":[210],"without":[211],"training":[218],"available":[222],"during":[223],"training.":[224],"experiments":[226],"several":[228],"collections":[229],"PhishMonger's":[231],"Targeted":[232],"Brand":[233],"dataset,":[234],"proposed":[236],"method":[237],"improvement":[240],"over":[241],"baseline":[243],"much":[246],"12%.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}