{"id":"https://openalex.org/W4313203541","doi":"https://doi.org/10.1109/tse.2022.3231621","title":"Learning Approximate Execution Semantics From Traces for Binary Function Similarity","display_name":"Learning Approximate Execution Semantics From Traces for Binary Function Similarity","publication_year":2022,"publication_date":"2022-12-28","ids":{"openalex":"https://openalex.org/W4313203541","doi":"https://doi.org/10.1109/tse.2022.3231621"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2022.3231621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3231621","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","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/A5058420386","display_name":"Kexin Pei","orcid":"https://orcid.org/0000-0001-5052-9808"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kexin Pei","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5052-9808","affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107249497","display_name":"Zhou Xuan","orcid":"https://orcid.org/0009-0000-5738-885X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou Xuan","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112881523","display_name":"Junfeng Yang","orcid":"https://orcid.org/0009-0004-9396-7882"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfeng Yang","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016425387","display_name":"Suman Jana","orcid":"https://orcid.org/0000-0002-9850-2169"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Jana","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064541855","display_name":"Baishakhi Ray","orcid":"https://orcid.org/0000-0003-3406-5235"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baishakhi Ray","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3406-5235","affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.066,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95244024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"49","issue":"4","first_page":"2776","last_page":"2790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T10260","display_name":"Software Engineering Research","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8609535694122314},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6111122965812683},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5867589712142944},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5763887763023376},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48696956038475037},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4750649631023407},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.44999635219573975},{"id":"https://openalex.org/keywords/operational-semantics","display_name":"Operational semantics","score":0.4410804510116577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2602486312389374},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1170366108417511},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08546140789985657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8609535694122314},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6111122965812683},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5867589712142944},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5763887763023376},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48696956038475037},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4750649631023407},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.44999635219573975},{"id":"https://openalex.org/C156325763","wikidata":"https://www.wikidata.org/wiki/Q1930895","display_name":"Operational semantics","level":3,"score":0.4410804510116577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2602486312389374},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1170366108417511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08546140789985657},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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:10.1109/tse.2022.3231621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3231621","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1147275914","display_name":null,"funder_award_id":"CNS-15-64055","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G2147521740","display_name":null,"funder_award_id":"CNS-18-01426","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G2292332785","display_name":null,"funder_award_id":"CNS-16-18771","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3747526932","display_name":null,"funder_award_id":"CNS-15-63843","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3890810436","display_name":null,"funder_award_id":"CNS-18-42456","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G5619927960","display_name":null,"funder_award_id":"CCF-16-19123","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G6856907612","display_name":null,"funder_award_id":"CCF-18-22965","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G7020628860","display_name":null,"funder_award_id":"CCF-18-45893","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G8325527411","display_name":null,"funder_award_id":"CNS-16-17670","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W65379173","https://openalex.org/W101604734","https://openalex.org/W145388748","https://openalex.org/W200653874","https://openalex.org/W844137998","https://openalex.org/W1690253345","https://openalex.org/W1851403712","https://openalex.org/W1942295288","https://openalex.org/W1965555277","https://openalex.org/W1974527629","https://openalex.org/W1984978725","https://openalex.org/W1995739251","https://openalex.org/W2009614414","https://openalex.org/W2012604743","https://openalex.org/W2048693719","https://openalex.org/W2051990174","https://openalex.org/W2136099030","https://openalex.org/W2165357553","https://openalex.org/W2165597437","https://openalex.org/W2532962075","https://openalex.org/W2547625248","https://openalex.org/W2577142429","https://openalex.org/W2602804099","https://openalex.org/W2619331983","https://openalex.org/W2627063456","https://openalex.org/W2729177083","https://openalex.org/W2731423391","https://openalex.org/W2749008552","https://openalex.org/W2767350860","https://openalex.org/W2886694146","https://openalex.org/W2896224010","https://openalex.org/W2896457183","https://openalex.org/W2898829570","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2933138175","https://openalex.org/W2948635572","https://openalex.org/W2948763287","https://openalex.org/W2950121745","https://openalex.org/W2955308964","https://openalex.org/W2963408280","https://openalex.org/W2963485370","https://openalex.org/W2963935794","https://openalex.org/W2986944522","https://openalex.org/W3000514891","https://openalex.org/W3007070494","https://openalex.org/W3007413911","https://openalex.org/W3010126799","https://openalex.org/W3011088748","https://openalex.org/W3033775865","https://openalex.org/W3043078865","https://openalex.org/W3044438666","https://openalex.org/W3105926539","https://openalex.org/W3107604447","https://openalex.org/W3108766814","https://openalex.org/W3109206613","https://openalex.org/W3111602563","https://openalex.org/W3111931266","https://openalex.org/W3127424491","https://openalex.org/W3133719257","https://openalex.org/W3137108338","https://openalex.org/W3137328154","https://openalex.org/W3137892723","https://openalex.org/W3155418077","https://openalex.org/W3162089186","https://openalex.org/W3164936723","https://openalex.org/W3168622027","https://openalex.org/W3170092793","https://openalex.org/W3194813479","https://openalex.org/W3196001856","https://openalex.org/W3208881055","https://openalex.org/W3211487307","https://openalex.org/W4205733352","https://openalex.org/W4252752212","https://openalex.org/W4281744374","https://openalex.org/W4287637491","https://openalex.org/W4385245566","https://openalex.org/W6602667510","https://openalex.org/W6608822657","https://openalex.org/W6617952372","https://openalex.org/W6629956336","https://openalex.org/W6631261549","https://openalex.org/W6639864006","https://openalex.org/W6640822829","https://openalex.org/W6743552807","https://openalex.org/W6743691393","https://openalex.org/W6745949993","https://openalex.org/W6751161574","https://openalex.org/W6762003241","https://openalex.org/W6763293644","https://openalex.org/W6765694979","https://openalex.org/W6766561868","https://openalex.org/W6783835735","https://openalex.org/W6784472380","https://openalex.org/W6784989367","https://openalex.org/W6791827149","https://openalex.org/W6792071449","https://openalex.org/W6793787349","https://openalex.org/W6794006112","https://openalex.org/W6796119419","https://openalex.org/W6840521041","https://openalex.org/W6869145669"],"related_works":["https://openalex.org/W2160196023","https://openalex.org/W1487966966","https://openalex.org/W1482532369","https://openalex.org/W2245685274","https://openalex.org/W2188386601","https://openalex.org/W3042312155","https://openalex.org/W2788308474","https://openalex.org/W2100934637","https://openalex.org/W3021003119","https://openalex.org/W3007870257"],"abstract_inverted_index":{"Detecting":[0],"semantically":[1,32,101,182],"similar":[2,33,102,183],"binary":[3],"functions":[4,34,54,192],"\u2013":[5,20,279],"a":[6,71,150],"crucial":[7],"capability":[8],"with":[9,44,210],"broad":[10],"security":[11],"usages":[12],"including":[13],"vulnerability":[14],"detection,":[15],"malware":[16],"analysis,":[17],"and":[18,25,43,94,144,169,207,209,222,235,240,300],"forensics":[19],"requires":[21],"understanding":[22,60],"function":[23,242,258],"behaviors":[24],"intentions.":[26],"This":[27],"task":[28],"is":[29,106,125],"challenging":[30],"as":[31],"can":[35,129],"be":[36,115,131],"compiled":[37,198],"to":[38,74,99,114,118,133,157,180,199],"run":[39,200],"on":[40,56,190,201,280],"different":[41],"architectures":[42,203],"diverse":[45,142],"compiler":[46],"optimizations":[47,212],"or":[48],"obfuscations.":[49,224],"Most":[50],"existing":[51],"approaches":[52],"match":[53,100,181],"based":[55],"syntactic":[57],"features":[58],"without":[59],"the":[61,90,96,155,163,172,177,229,253,257,262,272,298],"functions\u2019":[62,82],"execution":[63,78,139,160,266],"semantics.":[64,267],"We":[65,147,174,185,296],"present":[66],"<sc":[67,187,225,276,285,303],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[68,188,215,219,226,277,286,304,308],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Trex</small>":[69,189,227,278,287,305],",":[70],"transfer-learning-based":[72],"framework,":[73],"automate":[75],"learning":[76,265],"approximate":[77,138,159],"semantics":[79,140,161],"explicitly":[80],"from":[81,162,193],"traces":[83,110,128],"collected":[84],"via":[85],"forced-execution":[86,109],"(i.e.,":[87,166],"by":[88,232,293],"violating":[89],"control":[91],"flow":[92],"semantics)":[93],"transfer":[95],"learned":[97],"knowledge":[98],"functions.":[103,184],"While":[104],"it":[105],"known":[107],"that":[108,126,252],"are":[111],"too":[112],"imprecise":[113],"directly":[116],"used":[117,132],"detect":[119],"semantic":[120],"similarity,":[121],"our":[122],"key":[123],"insight":[124],"these":[127],"instead":[130],"teach":[134],"an":[135],"ML":[136],"model":[137,156,179],"of":[141,171,264,275,302],"instructions":[143],"their":[145],"compositions.":[146],"thus":[148],"design":[149],"pretraining":[151,254],"task,":[152],"which":[153],"trains":[154],"learn":[158],"two":[164],"modalities":[165],"forced-executed":[167],"code":[168,299],"traces)":[170],"function.":[173],"then":[175],"finetune":[176],"pretrained":[178],"evaluate":[186],"1,472,066":[191],"13":[194],"popular":[195],"software":[196],"projects,":[197],"4":[202,211],"(x86,":[204],"x64,":[205],"ARM,":[206],"MIPS),":[208],"(":[213],"<monospace":[214,218],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">O0</monospace>":[216],"-":[217],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">O3</monospace>":[220],")":[221],"5":[223],"outperforms":[228],"state-of-the-art":[230],"solutions":[231],"7.8%,":[233],"7.2%,":[234],"14.3%":[236],"in":[237],"cross-architecture,":[238],"optimization,":[239],"obfuscation":[241],"matching,":[243],"respectively,":[244],"while":[245],"running":[246],"8\u00d7":[247],"faster.":[248],"Ablation":[249],"studies":[250,270],"suggest":[251],"significantly":[255],"boosts":[256],"matching":[259],"performance,":[260],"underscoring":[261],"importance":[263],"Our":[268],"case":[269],"demonstrate":[271],"practical":[273],"use-cases":[274],"180":[281],"real-world":[282],"firmware":[283],"images,":[284],"uncovers":[288],"14":[289],"vulnerabilities":[290],"not":[291],"disclosed":[292],"previous":[294],"studies.":[295],"release":[297],"dataset":[301],"at":[306],"<uri":[307],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/CUMLSec/trex</uri>":[309],".":[310]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}