{"id":"https://openalex.org/W4306406265","doi":"https://doi.org/10.1145/3545948.3545956","title":"BinProv: Binary Code Provenance Identification without Disassembly","display_name":"BinProv: Binary Code Provenance Identification without Disassembly","publication_year":2022,"publication_date":"2022-10-17","ids":{"openalex":"https://openalex.org/W4306406265","doi":"https://doi.org/10.1145/3545948.3545956"},"language":"en","primary_location":{"id":"doi:10.1145/3545948.3545956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3545948.3545956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3545948.3545956","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Symposium on Research in Attacks, Intrusions and Defenses","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3545948.3545956","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100432158","display_name":"Xu He","orcid":"https://orcid.org/0000-0002-7032-6618"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xu He","raw_affiliation_strings":["George Mason University, United States"],"affiliations":[{"raw_affiliation_string":"George Mason University, United States","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070346269","display_name":"Shu Wang","orcid":"https://orcid.org/0000-0002-7920-7025"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu Wang","raw_affiliation_strings":["George Mason University, United States of America"],"affiliations":[{"raw_affiliation_string":"George Mason University, United States of America","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021740010","display_name":"Yunlong Xing","orcid":"https://orcid.org/0000-0002-3844-2467"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunlong Xing","raw_affiliation_strings":["George Mason University, United States of America"],"affiliations":[{"raw_affiliation_string":"George Mason University, United States of America","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785225","display_name":"Pengbin Feng","orcid":"https://orcid.org/0009-0001-8207-1472"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengbin Feng","raw_affiliation_strings":["George Mason University, United States of America"],"affiliations":[{"raw_affiliation_string":"George Mason University, United States of America","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664241","display_name":"Haining Wang","orcid":"https://orcid.org/0000-0002-9665-7511"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haining Wang","raw_affiliation_strings":["Virginia Tech, United States of America"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, United States of America","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350165","display_name":"Qi Li","orcid":"https://orcid.org/0000-0001-8776-8730"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065505890","display_name":"Songqing Chen","orcid":"https://orcid.org/0000-0003-4650-7125"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songqing Chen","raw_affiliation_strings":["George Mason University, United States of America"],"affiliations":[{"raw_affiliation_string":"George Mason University, United States of America","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026728546","display_name":"Kun Sun","orcid":"https://orcid.org/0000-0003-4152-2107"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Sun","raw_affiliation_strings":["George Mason University, United States of America"],"affiliations":[{"raw_affiliation_string":"George Mason University, United States of America","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100432158"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":4.7803,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95428405,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9984999895095825,"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":0.9984999895095825,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8423557281494141},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5926398634910583},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5354395508766174},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.5014612674713135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4958833158016205},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.4948844313621521},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46002689003944397},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44752585887908936},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.42233407497406006},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3382205665111542},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.2669273614883423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423557281494141},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5926398634910583},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5354395508766174},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5014612674713135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4958833158016205},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.4948844313621521},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46002689003944397},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44752585887908936},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.42233407497406006},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3382205665111542},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.2669273614883423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3545948.3545956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3545948.3545956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3545948.3545956","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Symposium on Research in Attacks, Intrusions and Defenses","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3545948.3545956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3545948.3545956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3545948.3545956","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Symposium on Research in Attacks, Intrusions and Defenses","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3823192631","display_name":null,"funder_award_id":"C-0008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6866416028","display_name":"Collaborative Research: CNS Core: Small: From Capture to Consumption: System Challenges in Pervasive 360-Degree Video Sharing","funder_award_id":"2007153","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7155321176","display_name":null,"funder_award_id":"62132011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306406265.pdf","grobid_xml":"https://content.openalex.org/works/W4306406265.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1779974843","https://openalex.org/W2102833942","https://openalex.org/W2111338655","https://openalex.org/W2166462894","https://openalex.org/W2250539671","https://openalex.org/W2514974017","https://openalex.org/W2532962075","https://openalex.org/W2577142429","https://openalex.org/W2749008552","https://openalex.org/W2888698761","https://openalex.org/W2945316254","https://openalex.org/W2997993688","https://openalex.org/W3014215579","https://openalex.org/W3043236449","https://openalex.org/W3105926539","https://openalex.org/W3109206613","https://openalex.org/W3137108338","https://openalex.org/W3166956180","https://openalex.org/W4247464060"],"related_works":["https://openalex.org/W2357088637","https://openalex.org/W2598672065","https://openalex.org/W3120610872","https://openalex.org/W2523911541","https://openalex.org/W1638297612","https://openalex.org/W2912361785","https://openalex.org/W4389751695","https://openalex.org/W2992632505","https://openalex.org/W2765199869","https://openalex.org/W2786676889"],"abstract_inverted_index":{"Provenance":[0],"identification,":[1],"which":[2,97,115],"is":[3,63,213],"essential":[4],"for":[5,17,175],"binary":[6,139,196,208,246],"analysis,":[7],"aims":[8],"to":[9,39,65,101,127,217],"uncover":[10],"the":[11,19,22,41,72,79,90,131,138,144,158,161,168,172,220,243],"specific":[12,95,176],"compiler":[13,238],"and":[14,28,34,57,129,134,147,160,188,195,241],"configuration":[15],"used":[16],"generating":[18],"executable.":[20],"Traditionally,":[21],"existing":[23],"solutions":[24],"extract":[25],"syntactic,":[26],"structural,":[27],"semantic":[29],"features":[30,80],"from":[31,71,122,137],"disassembled":[32],"programs":[33],"employ":[35],"machine":[36,82],"learning":[37,83],"techniques":[38],"identify":[40,237],"compilation":[42],"provenance":[43,111,152,177,225],"of":[44,93,245],"binaries.":[45,76],"However,":[46],"their":[47],"effectiveness":[48],"heavily":[49],"relies":[50],"on":[51,89,206],"disassembly":[52],"tools":[53],"(e.g.,":[54],"IDA":[55],"Pro)":[56],"tedious":[58],"feature":[59,149],"engineering,":[60],"since":[61],"it":[62],"challenging":[64],"obtain":[66],"accurate":[67],"assembly":[68],"code,":[69,209],"particularly,":[70],"stripped":[73],"or":[74],"obfuscated":[75,207],"In":[77,104],"addition,":[78],"in":[81,151,223],"approaches":[84],"are":[85],"manually":[86],"selected":[87],"based":[88,124],"domain":[91],"knowledge":[92],"one":[94],"architecture,":[96],"cannot":[98],"be":[99],"applied":[100],"other":[102],"architectures.":[103],"this":[105],"paper,":[106],"we":[107],"develop":[108],"an":[109],"end-to-end":[110],"identification":[112,178,226],"system":[113],"BinProv,":[114],"leverages":[116],"a":[117,214],"BERT":[118],"(Bidirectional":[119],"Encoder":[120],"Representations":[121],"Transformers)":[123],"embedding":[125,173],"model":[126,170],"learn":[128],"represent":[130],"context":[132],"semantics":[133],"syntax":[135],"directly":[136],"code.":[140],"Therefore,":[141],"BinProv":[142,155,184,203,212,234],"avoids":[143],"disassembling":[145],"step":[146],"manual":[148],"selection":[150],"identification.":[153],"Moreover,":[154],"can":[156,235],"distinguish":[157],"compilers":[159],"four":[162],"optimization":[163],"levels":[164],"(O0/O1/O2/O3)":[165],"by":[166],"fine-tuning":[167],"classifier":[169],"with":[171],"inputs":[174],"tasks.":[179,227],"Experimental":[180],"results":[181],"show":[182,232],"that":[183,202,211,233],"achieves":[185],"92.14%,":[186],"99.4%,":[187],"99.8%":[189],"accuracy":[190],"at":[191],"byte":[192],"sequence,":[193],"function,":[194],"levels,":[197],"respectively.":[198],"We":[199],"further":[200],"demonstrate":[201],"works":[204],"well":[205],"suggesting":[210],"viable":[215],"approach":[216],"remarkably":[218],"mitigate":[219],"disassembler":[221],"dependence":[222],"future":[224],"Finally,":[228],"our":[229],"case":[230],"studies":[231],"better":[236],"helper":[239],"functions":[240],"improve":[242],"performance":[244],"code":[247],"similarity":[248],"detection.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}