{"id":"https://openalex.org/W4409217153","doi":"https://doi.org/10.3390/e27040392","title":"GBsim: A Robust GCN-BERT Approach for Cross-Architecture Binary Code Similarity Analysis","display_name":"GBsim: A Robust GCN-BERT Approach for Cross-Architecture Binary Code Similarity Analysis","publication_year":2025,"publication_date":"2025-04-07","ids":{"openalex":"https://openalex.org/W4409217153","doi":"https://doi.org/10.3390/e27040392","pmid":"https://pubmed.ncbi.nlm.nih.gov/40282627"},"language":"en","primary_location":{"id":"doi:10.3390/e27040392","doi":"https://doi.org/10.3390/e27040392","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27040392","pdf_url":"https://www.mdpi.com/1099-4300/27/4/392/pdf?version=1744020289","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/27/4/392/pdf?version=1744020289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103600259","display_name":"Jiang Yi Du","orcid":"https://orcid.org/0009-0005-2125-7061","observed_orcids":["https://orcid.org/0009-0005-2125-7061"]},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Du","raw_affiliation_strings":["School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China"],"raw_orcid":"https://orcid.org/0009-0005-2125-7061","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000792418","display_name":"Qiang Wei","orcid":"https://orcid.org/0000-0002-7207-6691","observed_orcids":["https://orcid.org/0000-0002-7207-6691"]},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wei","raw_affiliation_strings":["School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101431030","display_name":"Yisen Wang","orcid":"https://orcid.org/0000-0002-0181-2137","observed_orcids":["https://orcid.org/0000-0002-0181-2137"]},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yisen Wang","raw_affiliation_strings":["School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100526509","display_name":"Xingyu Bai","orcid":"https://orcid.org/0000-0001-5410-0064","observed_orcids":["https://orcid.org/0000-0001-5410-0064","https://orcid.org/0009-0003-5171-1072"]},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Bai","raw_affiliation_strings":["School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Information Engineering University, Zhengzhou 450001, China","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101431030"],"corresponding_institution_ids":["https://openalex.org/I169689159"],"apc_list":{"value":2600,"currency":"CHF","value_usd":3137},"apc_paid":{"value":2600,"currency":"CHF","value_usd":3137},"fwci":2.1563,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89226159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"27","issue":"4","first_page":"392","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9545999765396118,"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":0.9545999765396118,"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/T11424","display_name":"Security and Verification in Computing","score":0.02810000069439411,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.005100000184029341,"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/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.8849999904632568},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.8240000009536743},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.7649999856948853},{"id":"https://openalex.org/keywords/vulnerability-detection","display_name":"vulnerability detection","score":0.8149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938472032546997},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4865764379501343},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.46325287222862244},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.45173180103302},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42470136284828186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42258864641189575},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41869574785232544},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4158194065093994},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38762491941452026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36599183082580566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3634156584739685},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11374464631080627},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/e27040392","doi":"https://doi.org/10.3390/e27040392","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27040392","pdf_url":"https://www.mdpi.com/1099-4300/27/4/392/pdf?version=1744020289","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:40282627","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40282627","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12025366","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12025366","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:00c7c55879164640808fc181b8ac4537","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/00c7c55879164640808fc181b8ac4537","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 27, Iss 4, p 392 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/e27040392","doi":"https://doi.org/10.3390/e27040392","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27040392","pdf_url":"https://www.mdpi.com/1099-4300/27/4/392/pdf?version=1744020289","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5884828426","display_name":null,"funder_award_id":"2020YFB2010900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409217153.pdf","grobid_xml":"https://content.openalex.org/works/W4409217153.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1548500763","https://openalex.org/W1614298861","https://openalex.org/W1690253345","https://openalex.org/W2579698096","https://openalex.org/W2619017101","https://openalex.org/W2749008552","https://openalex.org/W2886694146","https://openalex.org/W2888698761","https://openalex.org/W2896457183","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2942259124","https://openalex.org/W2945316254","https://openalex.org/W2997915791","https://openalex.org/W3007413911","https://openalex.org/W3008760144","https://openalex.org/W3108936298","https://openalex.org/W3109206613","https://openalex.org/W4324007217","https://openalex.org/W4381050433","https://openalex.org/W4393034172","https://openalex.org/W4393160168","https://openalex.org/W4402443222","https://openalex.org/W4402457354"],"related_works":["https://openalex.org/W2134880816","https://openalex.org/W2111298487","https://openalex.org/W4308157887","https://openalex.org/W2510680828","https://openalex.org/W2055498716","https://openalex.org/W1984130439","https://openalex.org/W4386075138","https://openalex.org/W2371359060","https://openalex.org/W2562873141","https://openalex.org/W2279238589"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,11,24,41,84,206,233],"graph":[3,42,112],"neural":[4,113],"networks":[5,114],"have":[6],"transformed":[7],"structural":[8,137],"pattern":[9],"learning":[10],"domains":[12],"ranging":[13],"from":[14,220],"social":[15],"network":[16],"analysis":[17],"to":[18,125,145,223],"biomolecular":[19],"modeling.":[20],"Nevertheless,":[21],"practical":[22,204],"deployments":[23],"mission-critical":[25],"scenarios":[26],"such":[27,74],"as":[28],"binary":[29,52,127],"code":[30],"similarity":[31],"detection":[32,187],"face":[33],"two":[34],"fundamental":[35],"obstacles:":[36],"first,":[37],"the":[38,56,234],"inherent":[39],"noise":[40,237],"construction":[43],"processes":[44],"exemplified":[45],"by":[46,61,214],"incomplete":[47],"control":[48],"flow":[49],"edges":[50],"during":[51],"function":[53],"recovery;":[54],"second,":[55],"substantial":[57],"distribution":[58,159,239],"discrepancies":[59],"caused":[60],"cross-architecture":[62,122,151,166],"instruction":[63],"set":[64],"variations.":[65],"Conventional":[66],"GNN":[67],"architectures":[68],"demonstrate":[69],"severe":[70],"performance":[71,156,217],"degradation":[72],"under":[73],"low":[75],"signal-to-noise":[76],"ratio":[77],"conditions":[78],"and":[79,140,176,210,238],"cross-domain":[80],"operational":[81],"environments,":[82],"particularly":[83],"security-sensitive":[85],"vulnerability":[86,186,200],"identification":[87],"tasks":[88],"where":[89],"feature":[90,138],"instability":[91],"or":[92],"domain":[93],"shifts":[94],"could":[95],"trigger":[96],"critical":[97],"false":[98],"judgments.":[99],"To":[100],"address":[101],"these":[102],"challenges,":[103],"we":[104],"propose":[105],"GBsim,":[106],"a":[107,121,133,142,164,177,198],"novel":[108],"approach":[109],"that":[110,153,169],"combines":[111],"with":[115],"natural":[116],"language":[117,123],"processing.":[118],"GBsim":[119,170,189],"employs":[120,141],"model":[124,231],"transform":[126],"functions":[128],"into":[129],"semantic":[130,147],"graphs,":[131],"leverages":[132],"multilayer":[134],"GCN":[135],"for":[136],"extraction,":[139],"Transformer":[143],"layer":[144],"integrate":[146],"information,":[148],"generates":[149],"robust":[150],"embeddings":[152],"maintain":[154],"high":[155],"despite":[157],"significant":[158],"shifts.":[160,240],"Extensive":[161],"experiments":[162],"on":[163,197],"large-scale":[165],"dataset":[167],"show":[168],"achieves":[171,190],"an":[172,191],"MRR":[173],"of":[174,179,195,236],"0.901":[175],"Recall@1":[178],"0.831,":[180],"outperforming":[181,211],"state-of-the-art":[182],"methods.":[183],"In":[184],"real-world":[185],"tasks,":[188],"average":[192],"recall":[193],"rate":[194],"81.3%":[196],"1-day":[199],"dataset,":[201],"demonstrating":[202],"its":[203],"effectiveness":[205],"identifying":[207],"security":[208],"threats":[209],"existing":[212],"methods":[213],"2.1%.":[215],"This":[216],"advantage":[218],"stems":[219],"GBsim's":[221],"ability":[222],"maximize":[224],"information":[225],"preservation":[226],"across":[227],"architectural":[228],"boundaries,":[229],"enhancing":[230],"robustness":[232],"presence":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}