{"id":"https://openalex.org/W4289313429","doi":"https://doi.org/10.1186/s42400-022-00119-8","title":"On building machine learning pipelines for Android malware detection: a procedural survey of practices, challenges and opportunities","display_name":"On building machine learning pipelines for Android malware detection: a procedural survey of practices, challenges and opportunities","publication_year":2022,"publication_date":"2022-08-02","ids":{"openalex":"https://openalex.org/W4289313429","doi":"https://doi.org/10.1186/s42400-022-00119-8"},"language":"en","primary_location":{"id":"doi:10.1186/s42400-022-00119-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42400-022-00119-8","pdf_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-022-00119-8","source":{"id":"https://openalex.org/S3035238565","display_name":"Cybersecurity","issn_l":"2523-3246","issn":["2523-3246"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybersecurity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-022-00119-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085274243","display_name":"Masoud Mehrabi Koushki","orcid":"https://orcid.org/0000-0002-0015-5753"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Masoud Mehrabi Koushki","raw_affiliation_strings":["Huawei Technologies Canada Co., Ltd, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada Co., Ltd, Vancouver, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028941501","display_name":"Ibrahim Abualhaol","orcid":"https://orcid.org/0000-0001-8359-4470"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ibrahim AbuAlhaol","raw_affiliation_strings":["Huawei Technologies Canada Co., Ltd, Ottawa, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada Co., Ltd, Ottawa, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022932578","display_name":"Anandharaju Durai Raju","orcid":"https://orcid.org/0000-0001-9873-5870"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anandharaju Durai Raju","raw_affiliation_strings":["Simon Fraser University, Burnaby, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, Vancouver, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030808791","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0001-9057-6713"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["Huawei Technologies Canada Co., Ltd, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada Co., Ltd, Toronto, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056993180","display_name":"Ronnie Salvador Giagone","orcid":"https://orcid.org/0000-0002-7877-9531"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ronnie Salvador Giagone","raw_affiliation_strings":["Huawei Technologies Canada Co., Ltd, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada Co., Ltd, Vancouver, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054235059","display_name":"Shengqiang Huang","orcid":"https://orcid.org/0000-0001-9137-0178"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Huang Shengqiang","raw_affiliation_strings":["Huawei Technologies Canada Co., Ltd, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada Co., Ltd, Vancouver, Canada","institution_ids":["https://openalex.org/I4210115038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085274243"],"corresponding_institution_ids":["https://openalex.org/I4210115038"],"apc_list":null,"apc_paid":null,"fwci":2.5452,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89994716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":"1","first_page":null,"last_page":null},"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":0.9952999949455261,"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":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.748468279838562},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.6740955114364624},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.6591765880584717},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6385665535926819},{"id":"https://openalex.org/keywords/malware-analysis","display_name":"Malware analysis","score":0.5430476069450378},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.526362955570221},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4211037755012512},{"id":"https://openalex.org/keywords/best-practice","display_name":"Best practice","score":0.4137054681777954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4120730757713318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41153138875961304},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36499303579330444},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3011298179626465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748468279838562},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.6740955114364624},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.6591765880584717},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6385665535926819},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.5430476069450378},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.526362955570221},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4211037755012512},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.4137054681777954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4120730757713318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41153138875961304},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36499303579330444},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3011298179626465},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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:10.1186/s42400-022-00119-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42400-022-00119-8","pdf_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-022-00119-8","source":{"id":"https://openalex.org/S3035238565","display_name":"Cybersecurity","issn_l":"2523-3246","issn":["2523-3246"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybersecurity","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d76c9d6a08f6425abbbfa4e5cbfc2f7d","is_oa":true,"landing_page_url":"https://doaj.org/article/d76c9d6a08f6425abbbfa4e5cbfc2f7d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cybersecurity, Vol 5, Iss 1, Pp 1-37 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s42400-022-00119-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42400-022-00119-8","pdf_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-022-00119-8","source":{"id":"https://openalex.org/S3035238565","display_name":"Cybersecurity","issn_l":"2523-3246","issn":["2523-3246"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybersecurity","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289313429.pdf","grobid_xml":"https://content.openalex.org/works/W4289313429.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W7469215","https://openalex.org/W79549259","https://openalex.org/W121173099","https://openalex.org/W1647869403","https://openalex.org/W1943233084","https://openalex.org/W1984008582","https://openalex.org/W1990649188","https://openalex.org/W1994216910","https://openalex.org/W1997199359","https://openalex.org/W1999728176","https://openalex.org/W2002478203","https://openalex.org/W2003276999","https://openalex.org/W2007857904","https://openalex.org/W2018316318","https://openalex.org/W2024071684","https://openalex.org/W2026875669","https://openalex.org/W2037026906","https://openalex.org/W2041276426","https://openalex.org/W2046843253","https://openalex.org/W2059043756","https://openalex.org/W2060537671","https://openalex.org/W2077278164","https://openalex.org/W2080157505","https://openalex.org/W2087970742","https://openalex.org/W2092942461","https://openalex.org/W2108700604","https://openalex.org/W2110889728","https://openalex.org/W2111487235","https://openalex.org/W2125011234","https://openalex.org/W2132449440","https://openalex.org/W2148952798","https://openalex.org/W2165698076","https://openalex.org/W2167003418","https://openalex.org/W2168103835","https://openalex.org/W2168347639","https://openalex.org/W2313513770","https://openalex.org/W2324464293","https://openalex.org/W2342408547","https://openalex.org/W2407313496","https://openalex.org/W2536311873","https://openalex.org/W2566281548","https://openalex.org/W2587002069","https://openalex.org/W2591102410","https://openalex.org/W2599823825","https://openalex.org/W2603160474","https://openalex.org/W2612123163","https://openalex.org/W2732916693","https://openalex.org/W2737578512","https://openalex.org/W2767843091","https://openalex.org/W2782221274","https://openalex.org/W2789983203","https://openalex.org/W2790117856","https://openalex.org/W2792310543","https://openalex.org/W2803881474","https://openalex.org/W2807671950","https://openalex.org/W2825974271","https://openalex.org/W2849849680","https://openalex.org/W2885070483","https://openalex.org/W2900275727","https://openalex.org/W2963204406","https://openalex.org/W2963777745","https://openalex.org/W2984482968","https://openalex.org/W2986232939","https://openalex.org/W2992853260","https://openalex.org/W3007018545","https://openalex.org/W3008923560","https://openalex.org/W3013149459","https://openalex.org/W3016369654","https://openalex.org/W3044668093","https://openalex.org/W3099091571","https://openalex.org/W3174621618","https://openalex.org/W3175362003","https://openalex.org/W3193105927","https://openalex.org/W3211182750"],"related_works":["https://openalex.org/W2717179875","https://openalex.org/W4249118297","https://openalex.org/W2469507153","https://openalex.org/W2008790809","https://openalex.org/W2768892939","https://openalex.org/W4285507391","https://openalex.org/W3164408430","https://openalex.org/W2397240470","https://openalex.org/W2602767565","https://openalex.org/W170652726"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"the":[2,28,46,77,103,128,137,149,199],"smartphone":[3],"market":[4,40],"leader,":[5],"Android":[6,85],"has":[7,24,51,87,98],"been":[8],"a":[9,100,122,177,184,194],"prominent":[10],"target":[11],"for":[12,22,35,226,249],"malware":[13,54,86],"attacks.":[14],"The":[15],"number":[16,48],"of":[17,49,61,76,124,127,148,179,186,198],"malicious":[18],"applications":[19],"(apps)":[20],"identified":[21],"it":[23],"increased":[25],"continually":[26],"over":[27,95],"past":[29],"decade,":[30],"creating":[31],"an":[32,59],"immense":[33],"challenge":[34],"all":[36],"parties":[37],"involved.":[38],"For":[39],"holders":[41],"and":[42,109,134,167,228,232,246,251],"researchers,":[43],"in":[44,102,244],"particular,":[45],"large":[47],"samples":[50],"made":[52,88],"manual":[53],"detection":[55],"unfeasible,":[56],"leading":[57],"to":[58,69,91,105,131,190],"influx":[60],"research":[62,187],"that":[63],"investigate":[64],"Machine":[65],"Learning":[66],"(ML)":[67],"approaches":[68,79],"automate":[70],"this":[71,170,174,238],"process.":[72],"However,":[73],"while":[74,158],"some":[75],"proposed":[78],"achieve":[80],"high":[81],"performance,":[82],"rapidly":[83],"evolving":[84],"them":[89],"unable":[90],"maintain":[92],"their":[93,230],"accuracy":[94],"time.":[96],"This":[97],"created":[99],"need":[101],"community":[104],"conduct":[106],"further":[107],"research,":[108],"build":[110],"more":[111],"flexible":[112],"ML":[113,150,207],"pipelines.":[114],"Doing":[115],"so,":[116],"however,":[117],"is":[118],"currently":[119],"hindered":[120],"by":[121],"lack":[123],"systematic":[125],"overview":[126],"existing":[129,138],"literature,":[130,201],"learn":[132],"from":[133,237],"improve":[135],"upon":[136],"solutions.":[139],"Existing":[140],"survey":[141],"papers":[142],"often":[143],"focus":[144],"only":[145],"on":[146],"parts":[147],"process":[151],"(e.g.,":[152],"data":[153],"collection":[154],"or":[155],"model":[156,165],"deployment),":[157],"omitting":[159],"other":[160],"important":[161],"stages,":[162],"such":[163],"as":[164],"evaluation":[166,231],"explanation.":[168],"In":[169],"paper,":[171],"we":[172,240],"address":[173],"problem":[175],"with":[176],"review":[178],"42":[180],"highly-cited":[181],"papers,":[182],"spanning":[183],"decade":[185],"(from":[188],"2011":[189],"2021).":[191],"We":[192],"introduce":[193],"novel":[195],"procedural":[196],"taxonomy":[197],"published":[200],"covering":[202],"how":[203],"they":[204,211,218,223],"have":[205,212,219,224],"used":[206],"algorithms,":[208],"what":[209,221,229],"features":[210],"engineered,":[213],"which":[214],"dimensionality":[215],"reduction":[216],"techniques":[217],"employed,":[220],"datasets":[222],"employed":[225],"training,":[227],"explanation":[233],"strategies":[234],"are.":[235],"Drawing":[236],"taxonomy,":[239],"also":[241],"identify":[242],"gaps":[243],"knowledge":[245],"provide":[247],"ideas":[248],"improvement":[250],"future":[252],"work.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
