{"id":"https://openalex.org/W2985246627","doi":"https://doi.org/10.1093/comjnl/bxz121","title":"Byte2vec: Malware Representation and Feature Selection for Android","display_name":"Byte2vec: Malware Representation and Feature Selection for Android","publication_year":2019,"publication_date":"2019-09-05","ids":{"openalex":"https://openalex.org/W2985246627","doi":"https://doi.org/10.1093/comjnl/bxz121","mag":"2985246627"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxz121","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxz121","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},"type":"article","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/A5113885484","display_name":"Mahmood Yousefi\u2010Azar","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Mahmood Yousefi-Azar","raw_affiliation_strings":["Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039882547","display_name":"Len Hamey","orcid":"https://orcid.org/0000-0001-8594-2176"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Len Hamey","raw_affiliation_strings":["Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029458848","display_name":"Vijay Varadharajan","orcid":"https://orcid.org/0000-0002-3621-9114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijay Varadharajan","raw_affiliation_strings":["Faculty of Engineering and Built Environment, University of Newcastle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Built Environment, University of Newcastle","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043470959","display_name":"Shiping Chen","orcid":"https://orcid.org/0000-0002-4603-0024"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shiping Chen","raw_affiliation_strings":["Commonwealth Scientific and Industrial Research Organisation, CSIRO, Data61"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Commonwealth Scientific and Industrial Research Organisation, CSIRO, Data61","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039882547","https://openalex.org/A5113885484"],"corresponding_institution_ids":["https://openalex.org/I99043593"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.6677,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69843398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"63","issue":"8","first_page":"1125","last_page":"1138"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9940999746322632,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.991100013256073,"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":0.8098361492156982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8075988292694092},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6747877597808838},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.6533923745155334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5691069960594177},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5267899632453918},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4563193917274475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3994702398777008},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39530810713768005},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38906925916671753}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8098361492156982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075988292694092},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6747877597808838},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.6533923745155334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691069960594177},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5267899632453918},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4563193917274475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3994702398777008},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39530810713768005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38906925916671753},{"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:10.1093/comjnl/bxz121","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxz121","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},{"id":"pmh:uon:44462","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1452613","pdf_url":null,"source":{"id":"https://openalex.org/S4377196471","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W139044672","https://openalex.org/W1443099000","https://openalex.org/W1581009051","https://openalex.org/W2082058012","https://openalex.org/W2121749752","https://openalex.org/W2122672392","https://openalex.org/W2128873747","https://openalex.org/W2167003418","https://openalex.org/W2171033594","https://openalex.org/W2493916176","https://openalex.org/W2518866423","https://openalex.org/W2559655401","https://openalex.org/W2598939142","https://openalex.org/W2604272474","https://openalex.org/W2620844046","https://openalex.org/W2732916693","https://openalex.org/W2752241832","https://openalex.org/W2766101558","https://openalex.org/W2773446523","https://openalex.org/W2789766369","https://openalex.org/W2789983203","https://openalex.org/W2795845996","https://openalex.org/W2885072546","https://openalex.org/W2901033482","https://openalex.org/W2964136807","https://openalex.org/W3099388751","https://openalex.org/W4247200422","https://openalex.org/W6678051712","https://openalex.org/W6678885109","https://openalex.org/W6682691769","https://openalex.org/W6695159855","https://openalex.org/W6717848421","https://openalex.org/W6743618022","https://openalex.org/W6744031222","https://openalex.org/W6744391056","https://openalex.org/W6748786334","https://openalex.org/W6752560646","https://openalex.org/W6753312754","https://openalex.org/W6756305280","https://openalex.org/W6756428195"],"related_works":["https://openalex.org/W2097492617","https://openalex.org/W2753240997","https://openalex.org/W1764168690","https://openalex.org/W3152891574","https://openalex.org/W4284893819","https://openalex.org/W4316881845","https://openalex.org/W4232632923","https://openalex.org/W2775776836","https://openalex.org/W4323520309","https://openalex.org/W2018632273"],"abstract_inverted_index":{"Abstract":[0],"Malware":[1],"detection":[2,32,230],"based":[3],"on":[4,154,171,207,232],"static":[5,20,30],"features":[6,127],"and":[7,37,55,76,112,187,192,222],"without":[8],"code":[9],"disassembling":[10],"is":[11,141,168,188],"a":[12,43,71,79,109,118,183,208,215,223],"challenging":[13],"path":[14],"of":[15,22,49,66,86,145,211,219,227,238],"research.":[16],"Obfuscation":[17],"makes":[18],"the":[19,47,63,106,151,178,236,239,246],"analysis":[21],"malware":[23,31,59,100,132,159,164,213,234],"even":[24],"more":[25],"challenging.":[26],"This":[27],"paper":[28],"extends":[29],"beyond":[33],"byte":[34,67],"level":[35,68],"$n$-grams":[36],"detecting":[38],"important":[39],"strings.":[40],"We":[41,102,134,149],"propose":[42],"model":[44,167,179],"(Byte2vec)":[45],"with":[46,90,95,190,214,245],"capabilities":[48],"both":[50],"binary":[51],"file":[52],"feature":[53,56,72,84,110,138,185,241],"representation":[54],"selection":[57,139,242],"for":[58,99,131],"detection.":[60,101,133],"Byte2vec":[61],"embeds":[62],"semantic":[64],"similarity":[65],"codes":[69],"into":[70,78],"vector":[73,111,116],"(byte":[74],"vector)":[75],"also":[77,103],"context":[80,115],"vector.":[81],"The":[82,124,166,174,229],"learned":[83],"vectors":[85],"Byte2vec,":[87],"using":[88],"skip-gram":[89],"negative-sampling":[91],"topology,":[92],"are":[93,128],"combined":[94],"byte-level":[96],"term-frequency":[97],"(tf)":[98],"show":[104,135,176,203,235],"that":[105,136,177],"distance":[107],"between":[108],"its":[113],"corresponding":[114],"provides":[117],"useful":[119],"measure":[120],"to":[121],"rank":[122],"features.":[123],"top":[125],"ranked":[126],"successfully":[129],"used":[130],"this":[137],"algorithm":[140,243],"an":[142],"unsupervised":[143,240],"version":[144],"mutual":[146],"information":[147],"(MI).":[148],"test":[150],"proposed":[152],"scheme":[153],"four":[155],"freely":[156],"available":[157],"Android":[158],"datasets":[160],"including":[161],"one":[162],"obfuscated":[163,212,233],"dataset.":[165],"trained":[169],"only":[170,220],"clean":[172],"APKs.":[173],"results":[175,206,231],"outperforms":[180],"MI":[181,191],"in":[182,196],"low-dimensional":[184],"space":[186],"competitive":[189],"other":[193],"state-of-the-art":[194],"models":[195],"higher":[197],"dimensions.":[198],"In":[199],"particular,":[200],"our":[201],"tests":[202],"very":[204],"promising":[205],"wide":[209],"range":[210],"false":[216,224],"negative":[217],"rate":[218,226],"0.3%":[221],"positive":[225],"2.0%.":[228],"advantage":[237],"compared":[244],"MI-based":[247],"method.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
