{"id":"https://openalex.org/W3161331107","doi":"https://doi.org/10.1145/3446905","title":"On the Impact of Sample Duplication in Machine-Learning-Based Android Malware Detection","display_name":"On the Impact of Sample Duplication in Machine-Learning-Based Android Malware Detection","publication_year":2021,"publication_date":"2021-05-08","ids":{"openalex":"https://openalex.org/W3161331107","doi":"https://doi.org/10.1145/3446905","mag":"3161331107"},"language":"en","primary_location":{"id":"doi:10.1145/3446905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3446905","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbilu.uni.lu/handle/10993/49372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023970004","display_name":"Yanjie Zhao","orcid":"https://orcid.org/0000-0001-8793-5367"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yanjie Zhao","raw_affiliation_strings":["Monash University, Australia, Clayton, VIC"],"affiliations":[{"raw_affiliation_string":"Monash University, Australia, Clayton, VIC","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407830","display_name":"Li Li","orcid":"https://orcid.org/0000-0003-2990-1614"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Monash University, Australia, Clayton, VIC"],"affiliations":[{"raw_affiliation_string":"Monash University, Australia, Clayton, VIC","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427184","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0002-4314-6099"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, PRC, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, PRC, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076081056","display_name":"Haipeng Cai","orcid":"https://orcid.org/0000-0002-5224-9970"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haipeng Cai","raw_affiliation_strings":["Washington State University, United States, WA, USA"],"affiliations":[{"raw_affiliation_string":"Washington State University, United States, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082835974","display_name":"Tegawend\u00e9 F. Bissyand\u00e9","orcid":"https://orcid.org/0000-0001-7270-9869"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Tegawend\u00e9 F. Bissyand\u00e9","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040326968","display_name":"Jacques Klein","orcid":"https://orcid.org/0000-0003-4052-475X"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Jacques Klein","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016535521","display_name":"John G. Grundy","orcid":"https://orcid.org/0000-0002-2553-3976"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"John Grundy","raw_affiliation_strings":["Monash University, Australia, Clayton, VIC"],"affiliations":[{"raw_affiliation_string":"Monash University, Australia, Clayton, VIC","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5023970004"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":8.4882,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.98429039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":"3","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9873999953269958,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.8402918577194214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8385772705078125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7095233201980591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6722255945205688},{"id":"https://openalex.org/keywords/android-malware","display_name":"Android malware","score":0.6257425546646118},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.5967392921447754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33624231815338135},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08827438950538635}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8402918577194214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385772705078125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7095233201980591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6722255945205688},{"id":"https://openalex.org/C2989133298","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android malware","level":3,"score":0.6257425546646118},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.5967392921447754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33624231815338135},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08827438950538635},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3446905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3446905","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/49372","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/49372","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"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":null}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/49372","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/49372","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"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":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1408323592","display_name":null,"funder_award_id":"830892","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G393936824","display_name":null,"funder_award_id":"6170204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5304380016","display_name":null,"funder_award_id":"61702045 and 62072046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6031817756","display_name":"Cost-Efficient Methods and Processes for Safety Relevant Embedded Systems","funder_award_id":"100016","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G753796446","display_name":null,"funder_award_id":"61702045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W79549259","https://openalex.org/W1645479483","https://openalex.org/W1943233084","https://openalex.org/W2002478203","https://openalex.org/W2034938003","https://openalex.org/W2057079516","https://openalex.org/W2071536101","https://openalex.org/W2085700758","https://openalex.org/W2085807744","https://openalex.org/W2089481916","https://openalex.org/W2110889728","https://openalex.org/W2122672392","https://openalex.org/W2125011234","https://openalex.org/W2125283600","https://openalex.org/W2133571308","https://openalex.org/W2141198770","https://openalex.org/W2171389360","https://openalex.org/W2216498498","https://openalex.org/W2277576447","https://openalex.org/W2290781924","https://openalex.org/W2294381999","https://openalex.org/W2298229910","https://openalex.org/W2343325785","https://openalex.org/W2407313496","https://openalex.org/W2470899015","https://openalex.org/W2474835145","https://openalex.org/W2514847810","https://openalex.org/W2572070369","https://openalex.org/W2599823825","https://openalex.org/W2608489681","https://openalex.org/W2613948935","https://openalex.org/W2620844046","https://openalex.org/W2625739732","https://openalex.org/W2744863892","https://openalex.org/W2749928722","https://openalex.org/W2775172862","https://openalex.org/W2783327762","https://openalex.org/W2789983203","https://openalex.org/W2791541601","https://openalex.org/W2792310543","https://openalex.org/W2794510434","https://openalex.org/W2795678871","https://openalex.org/W2808617203","https://openalex.org/W2890086692","https://openalex.org/W2897812226","https://openalex.org/W2900890308","https://openalex.org/W2922089394","https://openalex.org/W2953797486","https://openalex.org/W2955308964","https://openalex.org/W2962861874","https://openalex.org/W2963213304","https://openalex.org/W2963463723","https://openalex.org/W2963548617","https://openalex.org/W2963580354","https://openalex.org/W2979792666","https://openalex.org/W2995340752","https://openalex.org/W2996826556","https://openalex.org/W3000627442","https://openalex.org/W3005140940","https://openalex.org/W3009677746","https://openalex.org/W3103123779","https://openalex.org/W3106500569","https://openalex.org/W4238972538","https://openalex.org/W4244726870","https://openalex.org/W4245027182","https://openalex.org/W4289710802","https://openalex.org/W6684801420"],"related_works":["https://openalex.org/W2560361988","https://openalex.org/W2507113366","https://openalex.org/W2591124010","https://openalex.org/W3200508744","https://openalex.org/W3025122950","https://openalex.org/W2311926078","https://openalex.org/W2895504842","https://openalex.org/W4281384336","https://openalex.org/W2717179875","https://openalex.org/W4249118297"],"abstract_inverted_index":{"Malware":[0],"detection":[1,28],"at":[2],"scale":[3],"in":[4,78],"the":[5,63,94,99,158],"Android":[6,151],"realm":[7],"is":[8],"often":[9],"carried":[10],"out":[11],"using":[12],"machine":[13,103],"learning":[14,104,120],"techniques.":[15],"State-of-the-art":[16],"approaches":[17],"such":[18,36],"as":[19],"DREBIN":[20],"and":[21,52,133],"MaMaDroid":[22],"are":[23,70],"reported":[24],"to":[25,61],"yield":[26],"high":[27],"rates":[29],"when":[30,68,142],"assessed":[31],"against":[32],"well-known":[33],"datasets.":[34],"Unfortunately,":[35],"datasets":[37,69,80],"may":[38,47],"include":[39],"a":[40,82],"large":[41],"portion":[42],"of":[43,96,102],"duplicated":[44],"samples,":[45],"which":[46],"bias":[48,105],"recorded":[49],"experimental":[50,73],"results":[51,74],"insights.":[53],"In":[54],"this":[55],"article,":[56],"we":[57,127],"perform":[58],"extensive":[59],"experiments":[60],"measure":[62],"performance":[64],"gap":[65],"that":[66,76,113,129],"occurs":[67],"de-duplicated.":[71],"Our":[72,109],"reveal":[75],"duplication":[77,115,139],"published":[79],"has":[81],"limited":[83],"impact":[84,159],"on":[85,98],"supervised":[86,147],"malware":[87,123,152],"classification":[88],"models.":[89],"This":[90],"observation":[91],"contrasts":[92],"with":[93],"finding":[95],"Allamanis":[97],"general":[100],"case":[101],"for":[106],"big":[107],"code.":[108],"experiments,":[110],"however,":[111],"show":[112],"sample":[114,138],"more":[116],"substantially":[117],"affects":[118],"unsupervised":[119,149],"models":[121],"(e.g.,":[122],"family":[124],"clustering).":[125],"Nevertheless,":[126],"argue":[128],"our":[130],"fellow":[131],"researchers":[132],"practitioners":[134],"should":[135],"always":[136],"take":[137],"into":[140],"consideration":[141],"performing":[143],"machine-learning-based":[144],"(via":[145],"either":[146],"or":[148],"learning)":[150],"detections,":[153],"no":[154],"matter":[155],"how":[156],"significant":[157],"might":[160],"be.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}