{"id":"https://openalex.org/W4400798708","doi":"https://doi.org/10.1145/3671016.3671390","title":"CRABS-former: CRoss-Architecture Binary Code Similarity Detection based on Transformer","display_name":"CRABS-former: CRoss-Architecture Binary Code Similarity Detection based on Transformer","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400798708","doi":"https://doi.org/10.1145/3671016.3671390"},"language":"en","primary_location":{"id":"doi:10.1145/3671016.3671390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3671016.3671390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Asia-Pacific Symposium on Internetware","raw_type":"proceedings-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/A5101501973","display_name":"Yuhong Feng","orcid":"https://orcid.org/0000-0002-7691-5587"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhong Feng","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026011567","display_name":"Haoran Li","orcid":"https://orcid.org/0009-0007-6789-5573"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068733869","display_name":"Yunhe Cao","orcid":"https://orcid.org/0009-0006-6241-4251"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Cao","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104119576","display_name":"Yufeng Wang","orcid":"https://orcid.org/0009-0008-8710-4641"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Wang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060840648","display_name":"Haiyue Feng","orcid":"https://orcid.org/0009-0002-7239-3467"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyue Feng","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101501973"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":2.5777,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91138446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9983999729156494,"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":0.9983999729156494,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9983000159263611,"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":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6336942911148071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6195676922798157},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.505936324596405},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.498746395111084},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45091894268989563},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4200063943862915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25443732738494873},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2191465198993683},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15237605571746826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13035282492637634},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.12215057015419006},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11462393403053284},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09184357523918152}],"concepts":[{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6336942911148071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6195676922798157},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.505936324596405},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.498746395111084},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45091894268989563},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4200063943862915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25443732738494873},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2191465198993683},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15237605571746826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13035282492637634},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.12215057015419006},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11462393403053284},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09184357523918152},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3671016.3671390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3671016.3671390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Asia-Pacific Symposium on Internetware","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1967185446","https://openalex.org/W2156858199","https://openalex.org/W2579698096","https://openalex.org/W2602804099","https://openalex.org/W2611949786","https://openalex.org/W2749008552","https://openalex.org/W2912500072","https://openalex.org/W2926178846","https://openalex.org/W2988200900","https://openalex.org/W2997915791","https://openalex.org/W3007413911","https://openalex.org/W3105926539","https://openalex.org/W3108936298","https://openalex.org/W3109206613","https://openalex.org/W3118658046","https://openalex.org/W3121165942","https://openalex.org/W3123969097","https://openalex.org/W3153398259","https://openalex.org/W4285586654","https://openalex.org/W4311166089","https://openalex.org/W4312324806","https://openalex.org/W4313203541","https://openalex.org/W4381050443","https://openalex.org/W4384154511","https://openalex.org/W4393156544"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2588198209","https://openalex.org/W2012019886","https://openalex.org/W1909006023","https://openalex.org/W3200723557","https://openalex.org/W2166090428","https://openalex.org/W4205824991","https://openalex.org/W2381021552","https://openalex.org/W2354749003"],"abstract_inverted_index":{"Binary":[0,159],"code":[1,71,90,106,139,160],"similarity":[2,183],"detection":[3,14,162],"(BCSD)":[4],"is":[5,25],"widely":[6],"used":[7],"in":[8,62,97],"software":[9],"analysis":[10],"such":[11,55,149],"as":[12,56],"vulnerability":[13],"and":[15,39,72,108,118,131,180,194,207,225,231],"malware":[16],"identification.":[17],"Among":[18],"various":[19],"forms":[20],"of":[21,51,69,75,104,112,136,218,237],"binary":[22,171],"representation,":[23],"assembly":[24,70,89,105,138],"particularly":[26],"feasible":[27],"for":[28,189],"real-world":[29],"applications":[30],"due":[31,65],"to":[32,37,66,87,99,127,147],"its":[33,199],"efficient":[34],"preprocessing":[35],"compared":[36],"graph":[38],"intermediate":[40],"representation":[41],"(IR).":[42],"Existing":[43],"assembly-based":[44],"methods":[45],"leverage":[46],"the":[47,67,73,101,110,144,235],"text":[48],"embedding":[49],"capabilities":[50],"pretrained":[52],"language":[53],"models":[54],"BERT,":[57],"which":[58],"still":[59],"encounter":[60],"limitations":[61],"cross-architecture":[63,76],"BCSD":[64,191],"characteristics":[68],"lack":[74],"vocabulary.":[77],"In":[78],"this":[79,153],"paper,":[80],"we":[81,123,155,186],"first":[82],"design":[83],"several":[84],"normalization":[85],"strategies":[86],"preprocess":[88],"from":[91,140,173],"multiple":[92,141],"instruction":[93],"set":[94],"architectures":[95],"(ISAs),":[96],"order":[98],"decrease":[100],"token":[102,129],"length":[103],"inputs":[107],"reduce":[109],"size":[111,217],"vocabulary,":[113],"thereby":[114],"improving":[115],"processing":[116,137],"efficiency":[117],"simplifying":[119],"model":[120,163],"structure.":[121],"Then,":[122],"propose":[124],"a":[125,133,157,215],"method":[126],"collect":[128],"instances":[130],"construct":[132],"tokenizer":[134],"capable":[135],"ISAs,":[142,175,229],"enhancing":[143],"model\u2019s":[145],"ability":[146],"interpret":[148],"code.":[150],"Based":[151],"on":[152,165],"tokenizer,":[154],"develop":[156],"CRoss-Architecture":[158],"Similarity":[161],"based":[164],"Transformer":[166],"(CRABS-former).":[167],"CRABS-former":[168],"compares":[169],"two":[170,190],"functions":[172],"different":[174,228],"compilers":[176],"or":[177],"optimization":[178],"options":[179],"computes":[181],"their":[182],"score.":[184],"Finally,":[185],"conduct":[187],"experiments":[188],"tasks":[192],"(one-to-one":[193],"one-to-many)":[195],"using":[196],"CRABS-former,":[197,213],"comparing":[198],"performance":[200],"against":[201],"four":[202],"baselines:":[203],"SAFE,":[204],"Trex,":[205],"jTrans,":[206],"TE3L.":[208],"The":[209],"results":[210],"indicate":[211],"that":[212],"with":[214],"pool":[216],"10,000,":[219],"improves":[220],"recall":[221],"by":[222],"10.85%,":[223],"18.02%,":[224],"3.33%":[226],"across":[227],"compilers,":[230],"optimizations,":[232],"respectively,":[233],"underscoring":[234],"effectiveness":[236],"our":[238],"approach.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
