{"id":"https://openalex.org/W4402443222","doi":"https://doi.org/10.1145/3650212.3652117","title":"CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection","display_name":"CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402443222","doi":"https://doi.org/10.1145/3650212.3652117"},"language":"en","primary_location":{"id":"doi:10.1145/3650212.3652117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650212.3652117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.18818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100743772","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-0536-5039"},"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":"Hao Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0536-5039","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101050114","display_name":"Zeyu Gao","orcid":"https://orcid.org/0009-0003-2318-9061"},"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":"Zeyu Gao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2318-9061","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460096","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-7894-8828"},"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":"Chao Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7894-8828","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000712575","display_name":"Mingyang Sun","orcid":"https://orcid.org/0009-0004-7858-9246"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0004-7858-9246","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022291585","display_name":"Yuchen Zhou","orcid":"https://orcid.org/0000-0002-7021-1183"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Zhou","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7021-1183","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019692903","display_name":"Han Qiu","orcid":"https://orcid.org/0000-0003-2678-8070"},"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":"Han Qiu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2678-8070","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101600503","display_name":"Xi Xiao","orcid":"https://orcid.org/0000-0003-1521-9542"},"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":"Xi Xiao","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1521-9542","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.1697,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.98937537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9977999925613403,"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":0.9977999925613403,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9944000244140625,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178205847740173},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.583137035369873},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5657073855400085},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5441367626190186},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4866843819618225},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3315795361995697},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20082804560661316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1943812370300293},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1397264301776886},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.06258124113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178205847740173},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.583137035369873},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5657073855400085},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5441367626190186},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4866843819618225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3315795361995697},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20082804560661316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1943812370300293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1397264301776886},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.06258124113082886},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3650212.3652117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650212.3652117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.18818","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.18818","pdf_url":"https://arxiv.org/pdf/2402.18818","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.18818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.18818","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.18818","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.18818","pdf_url":"https://arxiv.org/pdf/2402.18818","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402443222.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1690253345","https://openalex.org/W1942295288","https://openalex.org/W1967185446","https://openalex.org/W1974527629","https://openalex.org/W1990762361","https://openalex.org/W2009614414","https://openalex.org/W2012604743","https://openalex.org/W2112796928","https://openalex.org/W2439280908","https://openalex.org/W2532962075","https://openalex.org/W2559784535","https://openalex.org/W2577142429","https://openalex.org/W2579698096","https://openalex.org/W2602804099","https://openalex.org/W2602815560","https://openalex.org/W2611949786","https://openalex.org/W2618635610","https://openalex.org/W2627063456","https://openalex.org/W2749008552","https://openalex.org/W2768051178","https://openalex.org/W2790751137","https://openalex.org/W2806869036","https://openalex.org/W2886694146","https://openalex.org/W2888320512","https://openalex.org/W2888698761","https://openalex.org/W2897937925","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2945316254","https://openalex.org/W2963408280","https://openalex.org/W2963485370","https://openalex.org/W2963979492","https://openalex.org/W2997915791","https://openalex.org/W2998702515","https://openalex.org/W3007413911","https://openalex.org/W3010126799","https://openalex.org/W3011088748","https://openalex.org/W3015184307","https://openalex.org/W3035524453","https://openalex.org/W3098380913","https://openalex.org/W3105926539","https://openalex.org/W3127424491","https://openalex.org/W3133719257","https://openalex.org/W4210918116","https://openalex.org/W4244720976","https://openalex.org/W4285586654","https://openalex.org/W4311166089","https://openalex.org/W4313203541","https://openalex.org/W4313327243","https://openalex.org/W4313484237","https://openalex.org/W4375957616","https://openalex.org/W4381050433","https://openalex.org/W4383221378","https://openalex.org/W4384154511","https://openalex.org/W4384155563","https://openalex.org/W4387055195","https://openalex.org/W4394745954"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2350529538","https://openalex.org/W2076713575","https://openalex.org/W2014996787"],"abstract_inverted_index":{"Binary":[0],"code":[1,87,142],"similarity":[2,118],"detection":[3,197],"(BCSD)":[4],"is":[5,39,130],"a":[6,47,68,94,99,178,212],"fundamental":[7],"technique":[8],"for":[9,139,193],"various":[10],"applications.":[11],"Many":[12],"BCSD":[13,49,172,191],"solutions":[14],"have":[15,24],"been":[16],"proposed":[17],"recently,":[18],"which":[19,52,78,112,230],"mostly":[20],"are":[21,231],"embedding-based,":[22],"but":[23,227],"shown":[25],"limited":[26],"accuracy":[27,61,116],"and":[28,55,88,109,126,136,215,237],"efficiency":[29],"especially":[30],"when":[31],"the":[32,82,103,115,122,157,169,184,194,202,241],"volume":[33],"of":[34,75,84,117,159,171,181,207,221,234],"target":[35,76],"binaries":[36],"to":[37,58,72,105,132,189],"search":[38],"large.":[40],"To":[41,166],"address":[42],"this":[43,224],"issue,":[44],"we":[45,176],"propose":[46],"cost-effective":[48],"framework,":[50],"CEBin,":[51],"fuses":[53],"embedding-based":[54,70,125],"comparison-based":[56,95,127],"approaches":[57],"significantly":[59],"improve":[60],"while":[62],"minimizing":[63],"overheads.":[64],"Specifically,":[65],"CEBin":[66,129,160,199],"utilizes":[67,93],"refined":[69],"approach":[71,96],"extract":[73],"features":[74],"code,":[77],"efficiently":[79],"narrows":[80],"down":[81],"scope":[83],"candidate":[85,208],"similar":[86,141,203],"boosts":[89],"performance.":[90],"Then,":[91],"it":[92],"that":[97],"performs":[98],"pairwise":[100],"comparison":[101],"on":[102,152,223],"candidates":[104],"capture":[106],"more":[107,225],"nuanced":[108],"complex":[110],"relationships,":[111],"greatly":[113],"improves":[114],"detection.":[119],"By":[120],"bridging":[121],"gap":[123],"between":[124],"approaches,":[128],"able":[131],"provide":[133],"an":[134,217],"effective":[135],"efficient":[137],"solution":[138],"detecting":[140],"(including":[143],"vulnerable":[144],"ones)":[145],"in":[146,173,210],"large-scale":[147,179],"software":[148],"ecosystems.":[149],"Experimental":[150],"results":[151],"three":[153],"well-known":[154],"datasets":[155],"demonstrate":[156],"superiority":[158],"over":[161],"existing":[162],"state-of-the-art":[163],"(SOTA)":[164],"baselines.":[165],"further":[167],"evaluate":[168],"usefulness":[170],"real":[174],"world,":[175],"construct":[177],"benchmark":[180],"vulnerability,":[182],"offering":[183],"first":[185],"precise":[186],"evaluation":[187],"scheme":[188],"assess":[190],"methods":[192],"1-day":[195],"vulnerability":[196],"task.":[198],"could":[200],"identify":[201],"function":[204],"from":[205],"millions":[206],"functions":[209],"just":[211],"few":[213],"seconds":[214],"achieves":[216],"impressive":[218],"recall":[219],"rate":[220],"85.46%":[222],"practical":[226],"challenging":[228],"task,":[229],"several":[232],"order":[233],"magnitudes":[235],"faster":[236],"4.07\u00d7":[238],"better":[239],"than":[240],"best":[242],"SOTA":[243],"baseline.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}