{"id":"https://openalex.org/W4410552830","doi":"https://doi.org/10.1109/saner64311.2025.00043","title":"A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer","display_name":"A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410552830","doi":"https://doi.org/10.1109/saner64311.2025.00043"},"language":"en","primary_location":{"id":"doi:10.1109/saner64311.2025.00043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner64311.2025.00043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","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/A5049022467","display_name":"Hongwei Lu","orcid":"https://orcid.org/0000-0002-8887-8461"},"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":"Hanxiao Lu","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongyu Cai","orcid":null},"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":"Hongyu Cai","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064871355","display_name":"Yiming Liang","orcid":"https://orcid.org/0000-0001-9193-4789"},"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":"Yiming Liang","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069212547","display_name":"A. Bianchi","orcid":"https://orcid.org/0000-0003-0343-7497"},"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":"Antonio Bianchi","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":null,"display_name":"Z. Berkay Celik","orcid":null},"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":"Z. Berkay Celik","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04606155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9768000245094299,"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"}},"topics":[{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9768000245094299,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9498999714851379,"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/T10320","display_name":"Neural Networks and Applications","score":0.9117000102996826,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5984483361244202},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5477518439292908},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4691540002822876},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.45245230197906494},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3205476999282837},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.2656314969062805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21953630447387695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18173086643218994},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17639902234077454},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12000074982643127},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07112777233123779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5984483361244202},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5477518439292908},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4691540002822876},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.45245230197906494},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3205476999282837},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2656314969062805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21953630447387695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18173086643218994},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17639902234077454},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12000074982643127},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07112777233123779}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/saner64311.2025.00043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner64311.2025.00043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6062656956","display_name":null,"funder_award_id":"IIS-2229876","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2407386500","https://openalex.org/W2596142952","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2945316254","https://openalex.org/W3005515703","https://openalex.org/W3006334803","https://openalex.org/W3109206613","https://openalex.org/W3133719257","https://openalex.org/W3137108338","https://openalex.org/W3175941285","https://openalex.org/W3194813479","https://openalex.org/W4247464060","https://openalex.org/W4285586654","https://openalex.org/W4303648996","https://openalex.org/W4306406265","https://openalex.org/W4308632257","https://openalex.org/W4313203541","https://openalex.org/W4382246105","https://openalex.org/W4396712834","https://openalex.org/W4404368853","https://openalex.org/W6621201870","https://openalex.org/W6628233427","https://openalex.org/W6640212811","https://openalex.org/W6679775712","https://openalex.org/W6691815588","https://openalex.org/W6727469013","https://openalex.org/W6743691393","https://openalex.org/W6748641434","https://openalex.org/W6766673545","https://openalex.org/W6855705626","https://openalex.org/W6858726514"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Language":[0,30],"models":[1,20],"have":[2],"recently":[3],"been":[4],"applied":[5],"to":[6,44,80,112,149,163,206],"binary":[7,46,82,124,181,192],"analysis":[8,182,193],"tasks,":[9,194],"such":[10],"as":[11],"function":[12,16],"similarity":[13],"detection":[14],"and":[15,36,56,73,95,203,210],"signature":[17],"recovery.":[18],"These":[19],"typically":[21],"employ":[22],"a":[23,93,113,119,129,135,211],"two-stage":[24,208],"training":[25,131],"process:":[26],"pre-training":[27],"via":[28],"Masked":[29],"Modeling":[31],"(MLM)":[32],"on":[33,134],"machine":[34],"code":[35,47,52,83,125],"fine-tuning":[37],"for":[38,123,178],"specific":[39],"tasks.":[40,183],"While":[41],"MLM":[42],"helps":[43],"understand":[45],"structures,":[48],"it":[49],"ignores":[50],"essential":[51],"characteristics,":[53],"including":[54],"control":[55,70],"data":[57],"flow,":[58],"which":[59,110],"negatively":[60],"affect":[61],"model":[62,162],"generalization.":[63],"Recent":[64],"work":[65],"leverages":[66],"domain-specific":[67],"features":[68],"(e.g.,":[69],"flow":[71],"graphs":[72],"dynamic":[74],"execution":[75],"traces)":[76],"in":[77,170,190,201],"transformer-based":[78,121],"approaches":[79],"improve":[81],"semantic":[84],"understanding.":[85],"This":[86,156],"approach,":[87],"however,":[88],"involves":[89],"complex":[90],"feature":[91],"engineering,":[92],"cumbersome":[94],"time-consuming":[96],"process":[97,132],"that":[98,173],"can":[99,174],"introduce":[100,117],"predictive":[101],"uncertainty":[102],"when":[103,215],"dealing":[104],"with":[105],"stripped":[106],"or":[107],"obfuscated":[108,217],"code,":[109],"leads":[111],"performance":[114],"drop.":[115],"We":[116],"PROTST,":[118],"novel":[120],"methodology":[122],"embedding.":[126],"PROTST":[127,187],"employs":[128],"hierarchical":[130],"based":[133],"unique":[136],"tree-like":[137],"structure,":[138],"where":[139],"knowledge":[140],"progressively":[141],"flows":[142],"from":[143],"fundamental":[144],"tasks":[145,152],"at":[146,153],"the":[147,154,161],"root":[148],"more":[150],"specialized":[151],"leaves.":[155],"progressive":[157],"teacher-student":[158],"paradigm":[159],"allows":[160],"build":[164],"upon":[165],"previously":[166],"learned":[167],"knowledge,":[168],"resulting":[169],"high-quality":[171],"embeddings":[172],"be":[175],"effectively":[176],"leveraged":[177],"diverse":[179],"downstream":[180],"The":[184],"effectiveness":[185],"of":[186,198],"is":[188],"evaluated":[189],"seven":[191],"demonstrating":[195],"an":[196],"average":[197],"14.8%":[199],"improvement":[200,214],"F1":[202],"MRR":[204],"compared":[205],"traditional":[207],"training,":[209],"16.6":[212],"%":[213],"analyzing":[216],"code.":[218]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}