{"id":"https://openalex.org/W2963562762","doi":"https://doi.org/10.1109/tifs.2018.2885512","title":"The MalSource Dataset: Quantifying Complexity and Code Reuse in Malware Development","display_name":"The MalSource Dataset: Quantifying Complexity and Code Reuse in Malware Development","publication_year":2018,"publication_date":"2018-12-07","ids":{"openalex":"https://openalex.org/W2963562762","doi":"https://doi.org/10.1109/tifs.2018.2885512","mag":"2963562762"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2018.2885512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2018.2885512","pdf_url":null,"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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://e-archivo.uc3m.es/bitstreams/e60c2ac2-6db8-4ac0-a263-e1a3a9a07ef0/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007527066","display_name":"Alejandro Calleja","orcid":"https://orcid.org/0000-0002-9772-7606"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Calleja","raw_affiliation_strings":["Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9772-7606","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070199150","display_name":"Juan Tapiador","orcid":"https://orcid.org/0000-0002-4573-3967"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Tapiador","raw_affiliation_strings":["Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101938709","display_name":"Juan Caballero","orcid":"https://orcid.org/0000-0003-2962-1348"},"institutions":[{"id":"https://openalex.org/I4210162154","display_name":"IMDEA Software Institute","ror":"https://ror.org/04xvfkh51","country_code":"ES","type":"facility","lineage":["https://openalex.org/I105140100","https://openalex.org/I4210162154"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Caballero","raw_affiliation_strings":["IMDEA Software Institute, Pozuelo de Alarc\u00f3n, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMDEA Software Institute, Pozuelo de Alarc\u00f3n, Madrid, Spain","institution_ids":["https://openalex.org/I4210162154"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.1786,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98163801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"14","issue":"12","first_page":"3175","last_page":"3190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9997000098228455,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/malware","display_name":"Malware","score":0.847292423248291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8366214036941528},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.5523315072059631},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5510910749435425},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5277907252311707},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.48994773626327515},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48225122690200806},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46436282992362976},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4561258554458618},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45075199007987976},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.4504738748073578},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.42842021584510803},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.350456565618515},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.33490315079689026},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12271729111671448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08773425221443176},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08154386281967163}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.847292423248291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366214036941528},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.5523315072059631},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5510910749435425},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5277907252311707},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.48994773626327515},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48225122690200806},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46436282992362976},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4561258554458618},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45075199007987976},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.4504738748073578},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.42842021584510803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.350456565618515},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.33490315079689026},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12271729111671448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08773425221443176},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08154386281967163},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tifs.2018.2885512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2018.2885512","pdf_url":null,"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:e-archivo.uc3m.es:10016/34939","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/34939","pdf_url":"https://e-archivo.uc3m.es/bitstreams/e60c2ac2-6db8-4ac0-a263-e1a3a9a07ef0/download","source":{"id":"https://openalex.org/S4306400817","display_name":"e-Archivo (Carlos III University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I50357001","host_organization_name":"Universidad Carlos III de Madrid","host_organization_lineage":["https://openalex.org/I50357001"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:e-archivo.uc3m.es:10016/34939","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/34939","pdf_url":"https://e-archivo.uc3m.es/bitstreams/e60c2ac2-6db8-4ac0-a263-e1a3a9a07ef0/download","source":{"id":"https://openalex.org/S4306400817","display_name":"e-Archivo (Carlos III University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I50357001","host_organization_name":"Universidad Carlos III de Madrid","host_organization_lineage":["https://openalex.org/I50357001"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2779535181","display_name":null,"funder_award_id":"TIN2015-7013-R","funder_id":"https://openalex.org/F4320335204","funder_display_name":"Secretar\u00eda de Estado de Investigaci\u00f3n, Desarrollo e Innovaci\u00f3n"},{"id":"https://openalex.org/G5509543476","display_name":null,"funder_award_id":"TIN2016-79095-C2-2-R","funder_id":"https://openalex.org/F4320335204","funder_display_name":"Secretar\u00eda de Estado de Investigaci\u00f3n, Desarrollo e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320335204","display_name":"Secretar\u00eda de Estado de Investigaci\u00f3n, Desarrollo e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963562762.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W202500387","https://openalex.org/W619991674","https://openalex.org/W1463623766","https://openalex.org/W1494656132","https://openalex.org/W1505648523","https://openalex.org/W1506513518","https://openalex.org/W1509260479","https://openalex.org/W1650881334","https://openalex.org/W1698439592","https://openalex.org/W1900564928","https://openalex.org/W1940252083","https://openalex.org/W1940356531","https://openalex.org/W1964962870","https://openalex.org/W1994410397","https://openalex.org/W2038424968","https://openalex.org/W2057330156","https://openalex.org/W2075858644","https://openalex.org/W2076472201","https://openalex.org/W2081185166","https://openalex.org/W2082180526","https://openalex.org/W2095470000","https://openalex.org/W2095720311","https://openalex.org/W2101832700","https://openalex.org/W2104301886","https://openalex.org/W2109943392","https://openalex.org/W2111338655","https://openalex.org/W2114728368","https://openalex.org/W2128782367","https://openalex.org/W2138756793","https://openalex.org/W2157532207","https://openalex.org/W2163164637","https://openalex.org/W2171816001","https://openalex.org/W2213051614","https://openalex.org/W2296488620","https://openalex.org/W2298313545","https://openalex.org/W2334699878","https://openalex.org/W2344840125","https://openalex.org/W2515415680","https://openalex.org/W2547621596","https://openalex.org/W2551072204","https://openalex.org/W2602804099","https://openalex.org/W2614419969","https://openalex.org/W3213422946","https://openalex.org/W6619491599","https://openalex.org/W6629511204","https://openalex.org/W6630328912","https://openalex.org/W6636713437","https://openalex.org/W6640762838","https://openalex.org/W6697318023","https://openalex.org/W6704398640","https://openalex.org/W6804146335"],"related_works":["https://openalex.org/W1992074508","https://openalex.org/W2086523506","https://openalex.org/W2157322365","https://openalex.org/W2975512365","https://openalex.org/W2159730313","https://openalex.org/W2029181676","https://openalex.org/W2230906511","https://openalex.org/W4248875503","https://openalex.org/W2747273734","https://openalex.org/W2150191652"],"abstract_inverted_index":{"During":[0],"the":[1,4,35,43,58,79,123,161],"last":[2],"decades,":[3],"problem":[5],"of":[6,25,45,61,71,78,86,94,98,117,139,164],"malicious":[7],"and":[8,16,28,68,76,84,107,145,149,166],"unwanted":[9],"software":[10,53],"(malware)":[11],"has":[12,29],"surged":[13],"in":[14,23,34,102,131],"numbers":[15],"sophistication.":[17],"Malware":[18],"plays":[19],"a":[20,32,52,136],"key":[21],"role":[22],"most":[24],"today's":[26],"cyberattacks":[27],"consolidated":[30],"as":[31,105],"commodity":[33],"underground":[36],"economy.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"analyze":[42,57],"evolution":[44],"malware":[46,143,165],"from":[47,51,64],"1975":[48],"to":[49,115,125],"date":[50],"engineering":[54],"perspective.":[55],"We":[56,120,134],"source":[59],"code":[60,74,111,127,140],"456":[62],"samples":[63],"428":[65],"unique":[66],"families":[67,144],"obtain":[69],"measures":[70],"their":[72],"size,":[73],"quality,":[75],"estimates":[77],"development":[80],"costs":[81],"(effort,":[82],"time,":[83],"number":[85,138],"people).":[87],"Our":[88],"results":[89,157],"suggest":[90],"an":[91,171],"exponential":[92],"increment":[93],"nearly":[95],"one":[96],"order":[97],"magnitude":[99],"per":[100],"decade":[101],"aspects":[103],"such":[104],"size":[106],"estimated":[108],"effort,":[109],"with":[110],"quality":[112],"metrics":[113],"similar":[114],"those":[116],"benign":[118],"software.":[119],"also":[121],"study":[122],"extent":[124],"which":[126,147],"reuse":[128],"is":[129],"present":[130],"our":[132,156],"dataset.":[133],"detect":[135],"significant":[137],"clones":[141],"across":[142],"report":[146],"features":[148],"functionalities":[150],"are":[151],"more":[152],"commonly":[153],"shared.":[154],"Overall,":[155],"support":[158],"claims":[159],"about":[160],"increasing":[162],"complexity":[163],"its":[167],"production":[168],"progressively":[169],"becoming":[170],"industry.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2019-07-30T00:00:00"}
