{"id":"https://openalex.org/W3127424491","doi":"https://doi.org/10.1109/tse.2021.3056139","title":"Codee: A Tensor Embedding Scheme for Binary Code Search","display_name":"Codee: A Tensor Embedding Scheme for Binary Code Search","publication_year":2021,"publication_date":"2021-02-03","ids":{"openalex":"https://openalex.org/W3127424491","doi":"https://doi.org/10.1109/tse.2021.3056139","mag":"3127424491"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2021.3056139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3056139","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/A5101657623","display_name":"Jia Yang","orcid":"https://orcid.org/0000-0003-1469-0789"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Yang","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","Hubei Engineering Research Center on Big Data Security, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Hubei Engineering Research Center on Big Data Security, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038034507","display_name":"Cai Fu","orcid":"https://orcid.org/0000-0003-4536-3537"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai Fu","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","Hubei Engineering Research Center on Big Data Security, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Hubei Engineering Research Center on Big Data Security, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405233","display_name":"Xiao-Yang Liu","orcid":"https://orcid.org/0000-0002-9532-1709"},"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":"Xiao-Yang Liu","raw_affiliation_strings":["Electrical Engineering Department, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073376805","display_name":"Heng Yin","orcid":"https://orcid.org/0000-0002-8942-7742"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Yin","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","Hubei Engineering Research Center on Big Data Security, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Hubei Engineering Research Center on Big Data Security, Wuhan, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101657623"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":5.7084,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.96863086,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"48","issue":"7","first_page":"2224","last_page":"2244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9958000183105469,"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":0.9958000183105469,"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":0.9943000078201294,"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":0.9887999892234802,"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":0.7242177724838257},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.621152937412262},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5456552505493164},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.49727728962898254},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4658549427986145},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4462159276008606},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4210382103919983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3569177985191345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2887694239616394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19242224097251892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242177724838257},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.621152937412262},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5456552505493164},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.49727728962898254},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4658549427986145},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4462159276008606},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4210382103919983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3569177985191345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2887694239616394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19242224097251892},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":2,"locations":[{"id":"doi:10.1109/tse.2021.3056139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3056139","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"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt5t74h0rn","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/5t74h0rn","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Software Engineering, vol PP, iss 99","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3690697415","display_name":null,"funder_award_id":"62072200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5817064308","display_name":null,"funder_award_id":"61972448","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1504886279","https://openalex.org/W1888005072","https://openalex.org/W1984978725","https://openalex.org/W2012604743","https://openalex.org/W2018067627","https://openalex.org/W2030927653","https://openalex.org/W2038276547","https://openalex.org/W2043571470","https://openalex.org/W2048693719","https://openalex.org/W2076409662","https://openalex.org/W2110121428","https://openalex.org/W2112725702","https://openalex.org/W2145056020","https://openalex.org/W2164278908","https://openalex.org/W2344301613","https://openalex.org/W2432058664","https://openalex.org/W2528907418","https://openalex.org/W2532962075","https://openalex.org/W2547625248","https://openalex.org/W2572070369","https://openalex.org/W2577142429","https://openalex.org/W2579698096","https://openalex.org/W2588341850","https://openalex.org/W2620895032","https://openalex.org/W2622489478","https://openalex.org/W2741705590","https://openalex.org/W2749008552","https://openalex.org/W2762651502","https://openalex.org/W2801712578","https://openalex.org/W2805984327","https://openalex.org/W2886694146","https://openalex.org/W2888320512","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2945316254","https://openalex.org/W2962688040","https://openalex.org/W2962756421","https://openalex.org/W2963224980","https://openalex.org/W2963408280","https://openalex.org/W2963502184","https://openalex.org/W2997915791","https://openalex.org/W3007413911","https://openalex.org/W3011088748","https://openalex.org/W3105926539","https://openalex.org/W3153398259","https://openalex.org/W3183154439","https://openalex.org/W6636411187","https://openalex.org/W6743691393"],"related_works":["https://openalex.org/W2134880816","https://openalex.org/W2111298487","https://openalex.org/W4308157887","https://openalex.org/W2963758661","https://openalex.org/W2088296667","https://openalex.org/W2055498716","https://openalex.org/W2279238589","https://openalex.org/W4386075138","https://openalex.org/W1984130439","https://openalex.org/W3016499519"],"abstract_inverted_index":{"Given":[0],"a":[1,162,166,174,204],"target":[2],"binary":[3,6,30,52,62,101],"function,":[4],"the":[5,14,25,100,113,129,137,143,150,182,189,212,219,226,234,284],"code":[7,31,63,94,240,277],"search":[8,64,95,199,241,253,278],"retrieves":[9],"top-K":[10],"similar":[11,17,230],"functions":[12,18,232],"in":[13,60,161,233],"repository,":[15],"and":[16,42,44,97,142,246,258,269,275],"represent":[19],"that":[20],"they":[21],"are":[22,56],"compiled":[23],"from":[24],"same":[26],"source":[27],"codes.":[28,53],"Searching":[29],"is":[32],"particularly":[33],"challenging":[34],"due":[35],"to":[36,91,111,148,164,176,196,209,224],"large":[37],"variations":[38],"of":[39,51,140,287],"compiler":[40],"tool-chains":[41],"options":[43],"CPU":[45],"architectures,":[46],"as":[47,49,244,281],"well":[48],"thousands":[50],"Furthermore,":[54],"there":[55],"some":[57],"pivotal":[58],"issues":[59],"current":[61],"schemes,":[65,242,279],"including":[66],"inaccurate":[67],"text-based":[68],"or":[69,75],"token-based":[70],"analysis,":[71],"slow":[72],"graph":[73],"matching,":[74],"complex":[76],"deep":[77],"learning":[78,132],"processes.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,105,118,155,172,217],"present":[84],"an":[85,107,120],"unsupervised":[86],"tensor":[87,175,183,206],"embedding":[88,124,214],"scheme,":[89],"Codee,":[90],"carry":[92],"out":[93],"efficiently":[96],"accurately":[98],"at":[99],"function":[102,163,168,178,213],"level.":[103],"First,":[104],"use":[106,156,218],"NLP-based":[108],"neural":[109],"network":[110,130],"generate":[112,149,177],"semantic-aware":[114],"token":[115],"embedding.":[116,153],"Second,":[117],"propose":[119,203],"efficient":[121,198],"basic":[122,151,158],"block":[123,152,159],"generation":[125,261],"algorithm":[126,208],"based":[127,180],"on":[128,181],"representation":[131],"model.":[133],"We":[134,201],"learn":[135],"both":[136],"semantic":[138],"information":[139,147],"instructions":[141],"control":[144],"flow":[145],"structural":[146],"Then":[154],"all":[157],"embeddings":[160,179],"obtain":[165],"variable-length":[167,190],"feature":[169,256,260],"vector.":[170],"Third,":[171],"build":[173],"singular":[184],"value":[185],"decomposition,":[186],"which":[187],"compresses":[188],"vectors":[191,195],"into":[192],"short":[193],"fixed-length":[194],"facilitate":[197],"afterward.":[200],"further":[202],"dynamic":[205],"compression":[207],"incrementally":[210],"update":[211],"database.":[215],"Finally,":[216],"local":[220],"sensitive":[221],"hash":[222],"method":[223,289],"find":[225],"top-":[227],"<inline-formula><tex-math":[228],"notation=\"LaTeX\">$K$</tex-math></inline-formula>":[229],"matching":[231],"repository.":[235],"Compared":[236,271],"with":[237,272],"state-of-the-art":[238],"cross-optimization-level":[239,276],"such":[243,280],"Asm2Vec":[245],"DeepBinDiff,":[247],"our":[248,288],"scheme":[249],"achieves":[250],"higher":[251],"average":[252,285],"accuracy,":[254],"shorter":[255],"vectors,":[257],"faster":[259],"performance":[262],"using":[263],"four":[264],"datasets,":[265],"OpenSSL,":[266],"Coreutils,":[267],"libgmp":[268],"libcurl.":[270],"other":[273],"cross-platform":[274],"Gemini,":[282],"Safe,":[283],"recall":[286],"also":[290],"outperforms":[291],"others.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}