{"id":"https://openalex.org/W3175479455","doi":"https://doi.org/10.1145/3461666","title":"Large-scale and Robust Code Authorship Identification with Deep Feature Learning","display_name":"Large-scale and Robust Code Authorship Identification with Deep Feature Learning","publication_year":2021,"publication_date":"2021-07-19","ids":{"openalex":"https://openalex.org/W3175479455","doi":"https://doi.org/10.1145/3461666","mag":"3175479455"},"language":"en","primary_location":{"id":"doi:10.1145/3461666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461666","pdf_url":null,"source":{"id":"https://openalex.org/S4210174050","display_name":"ACM Transactions on Privacy and Security","issn_l":"2471-2566","issn":["2471-2566","2471-2574"],"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 Privacy and Security","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/A5042456819","display_name":"Mohammed Abuhamad","orcid":"https://orcid.org/0000-0002-3368-6024"},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Abuhamad","raw_affiliation_strings":["Loyola University Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loyola University Chicago","institution_ids":["https://openalex.org/I1925986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023828527","display_name":"Tamer Abuhmed","orcid":"https://orcid.org/0000-0001-9232-4843"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tamer Abuhmed","raw_affiliation_strings":["Sungkyunkwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077402873","display_name":"Aziz Mohaisen","orcid":"https://orcid.org/0000-0003-3227-2505"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mohaisen","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079230730","display_name":"DaeHun Nyang","orcid":"https://orcid.org/0000-0001-5183-891X"},"institutions":[{"id":"https://openalex.org/I4210132203","display_name":"Ewha Womans University Medical Center","ror":"https://ror.org/03exgrk66","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I138925566","https://openalex.org/I4210132203"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehun Nyang","raw_affiliation_strings":["Ewha Womans University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University","institution_ids":["https://openalex.org/I4210132203"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9795,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80560368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"24","issue":"4","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.998199999332428,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9944999814033508,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9868999719619751,"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":0.8392549157142639},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5935474038124084},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5764365196228027},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5731374025344849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5513602495193481},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5094669461250305},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4903836250305176},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.45985135436058044},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.42938217520713806},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40354689955711365},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21979132294654846},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18757760524749756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392549157142639},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5935474038124084},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5764365196228027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5731374025344849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5513602495193481},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5094669461250305},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4903836250305176},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.45985135436058044},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.42938217520713806},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40354689955711365},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21979132294654846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18757760524749756},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461666","pdf_url":null,"source":{"id":"https://openalex.org/S4210174050","display_name":"ACM Transactions on Privacy and Security","issn_l":"2471-2566","issn":["2471-2566","2471-2574"],"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 Privacy and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G829976734","display_name":null,"funder_award_id":"NRF-2016K1A1A2912757","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W13740476","https://openalex.org/W21996614","https://openalex.org/W54929040","https://openalex.org/W60493759","https://openalex.org/W90413272","https://openalex.org/W1529790664","https://openalex.org/W1560590842","https://openalex.org/W1903025644","https://openalex.org/W1979185006","https://openalex.org/W2010452235","https://openalex.org/W2029103396","https://openalex.org/W2044555705","https://openalex.org/W2054126054","https://openalex.org/W2078111377","https://openalex.org/W2082594235","https://openalex.org/W2092475127","https://openalex.org/W2095705004","https://openalex.org/W2102833942","https://openalex.org/W2104595931","https://openalex.org/W2110127053","https://openalex.org/W2119804197","https://openalex.org/W2128889245","https://openalex.org/W2129364433","https://openalex.org/W2129683917","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2151505086","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2205815960","https://openalex.org/W2581748289","https://openalex.org/W2602753196","https://openalex.org/W2736199118","https://openalex.org/W2742948365","https://openalex.org/W2779800059","https://openalex.org/W2891865791","https://openalex.org/W2896102499","https://openalex.org/W2906453189","https://openalex.org/W2911964244","https://openalex.org/W3004022289","https://openalex.org/W3004984289","https://openalex.org/W3082436168","https://openalex.org/W3101243405","https://openalex.org/W4206031910","https://openalex.org/W4231109964","https://openalex.org/W4240485910","https://openalex.org/W4245139594","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W2350278424","https://openalex.org/W2071432835","https://openalex.org/W4239401009","https://openalex.org/W4234371507","https://openalex.org/W1628824497","https://openalex.org/W2598672065","https://openalex.org/W1993817217","https://openalex.org/W3120610872","https://openalex.org/W1638297612","https://openalex.org/W2523911541"],"abstract_inverted_index":{"Successful":[0],"software":[1,6,33,61,76,89,99,289,296],"authorship":[2,20,90,100,111],"de-anonymization":[3],"has":[4],"both":[5],"forensics":[7],"applications":[8],"and":[9,71,97,118,152,228,242,244,306],"privacy":[10],"implications.":[11],"However,":[12],"the":[13,51,58,106,134,138,192,204,221],"process":[14,107],"requires":[15],"an":[16,199,209,266],"efficient":[17],"extraction":[18,23],"of":[19,24,53,60,67,108,165,176,201,212,234,268,273,288,308,320],"attributes.":[21],"The":[22,163],"such":[25],"attributes":[26,54],"is":[27,55,224,256],"very":[28],"challenging,":[29],"due":[30],"to":[31,43,63,125,132,150,187,226,258],"various":[32],"code":[34,45,155],"formats":[35],"from":[36,157],"executable":[37,278],"binaries":[38,297,322],"with":[39,46,181,198,265,277,300],"different":[40,47,301],"toolchain":[41],"provenance":[42],"source":[44],"programming":[48,236],"languages.":[49],"Moreover,":[50,220,311],"quality":[52],"bounded":[56],"by":[57,196],"availability":[59],"samples":[62,68,156,177],"a":[64,72,84,114,173,271],"certain":[65],"number":[66,175],"per":[69,178],"author":[70],"specific":[73],"size":[74],"for":[75,88,123,214,270,284,316],"samples.":[77],"To":[78],"this":[79,81],"end,":[80],"work":[82,167],"proposes":[83],"deep":[85,110],"Learning-based":[86],"approach":[87,104,136,184,223,281,313],"attribution,":[91],"that":[92],"facilitates":[93],"large-scale,":[94],"format-independent,":[95],"language-oblivious,":[96],"obfuscation-resilient":[98],"identification.":[101],"This":[102],"proposed":[103,135,222],"incorporates":[105],"learning":[109],"attribution":[112],"using":[113,262,323],"recurrent":[115],"neural":[116],"network,":[117],"ensemble":[119],"random":[120],"forest":[121],"classifier":[122],"scalability":[124],"de-anonymize":[126],"programmers.":[127],"Comprehensive":[128],"experiments":[129],"are":[130,298],"conducted":[131],"evaluate":[133],"over":[137,153],"entire":[139],"Google":[140],"Code":[141],"Jam":[142],"(GCJ)":[143],"dataset":[144,194],"across":[145],"all":[146,324],"years":[147],"(from":[148],"2008":[149],"2016)":[151],"real-world":[154,205],"1,987":[158],"public":[159],"repositories":[160],"on":[161,218],"GitHub.":[162,219],"results":[164,292],"our":[166,183,254,280,312],"show":[168],"high":[169],"accuracy":[170,200,211,267],"despite":[171],"requiring":[172],"smaller":[174],"author.":[179],"Experimenting":[180,276],"source-code,":[182],"allows":[185],"us":[186],"identify":[188,232],"8,903":[189],"GCJ":[190],"authors,":[191],"largest-scale":[193],"used":[195],"far,":[197],"92.3%.":[202],"Using":[203],"dataset,":[206],"we":[207],"achieved":[208],"identification":[210],"94.38%":[213],"745":[215],"C":[216,263],"programmers":[217,287,319],"resilient":[225],"language-specifics,":[227],"thus":[229],"it":[230],"can":[231],"authors":[233,245],"four":[235],"languages":[237,249],"(e.g.,":[238,250,261],"C,":[239],"C++,":[240],"Java,":[241],"Python),":[243],"writing":[246],"in":[247,327],"mixed":[248],"Java/C++,":[251],"Python/C++).":[252],"Finally,":[253],"system":[255],"resistant":[257],"sophisticated":[259],"obfuscation":[260],"Tigress)":[264],"93.42%":[269],"set":[272],"120":[274],"authors.":[275],"binaries,":[279],"achieves":[282,314],"95.74%":[283],"identifying":[285,317],"1,500":[286,318],"binaries.":[290],"Similar":[291],"were":[293],"obtained":[294],"when":[295],"generated":[299],"compilation":[302],"options,":[303],"optimization":[304],"levels,":[305],"removing":[307],"symbol":[309],"information.":[310],"93.86%":[315],"obfuscated":[321],"features":[325],"adopted":[326],"Obfuscator-LLVM":[328],"tool.":[329]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}