{"id":"https://openalex.org/W4285586654","doi":"https://doi.org/10.1145/3533767.3534367","title":"jTrans: jump-aware transformer for binary code similarity detection","display_name":"jTrans: jump-aware transformer for binary code similarity detection","publication_year":2022,"publication_date":"2022-07-15","ids":{"openalex":"https://openalex.org/W4285586654","doi":"https://doi.org/10.1145/3533767.3534367"},"language":"en","primary_location":{"id":"doi:10.1145/3533767.3534367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3533767.3534367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3533767.3534367","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3533767.3534367","any_repository_has_fulltext":null},"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":true,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109420698","display_name":"Wenjie Qu","orcid":"https://orcid.org/0009-0006-2907-008X"},"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":"Wenjie Qu","raw_affiliation_strings":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044390999","display_name":"Gilad Katz","orcid":"https://orcid.org/0000-0001-9478-7550"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gilad Katz","raw_affiliation_strings":["Ben-Gurion University of the Negev, Israel"],"affiliations":[{"raw_affiliation_string":"Ben-Gurion University of the Negev, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045006740","display_name":"Wenyu Zhu","orcid":"https://orcid.org/0000-0003-4299-2944"},"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":"Wenyu Zhu","raw_affiliation_strings":["Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013798655","display_name":"Zeyu Gao","orcid":"https://orcid.org/0000-0001-6771-5885"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Gao","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112309175","display_name":"Jianwei Zhuge","orcid":null},"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":"Jianwei Zhuge","raw_affiliation_strings":["Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460120","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-9881-5643"},"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, China / Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China / Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100743772"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":42.388,"has_fulltext":true,"cited_by_count":137,"citation_normalized_percentile":{"value":0.99863682,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9987999796867371,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9898999929428101,"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":0.7308750152587891},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6328549385070801},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6322473287582397},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.5084985494613647},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.4767773449420929},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45579278469085693},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45369720458984375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.429245263338089},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.411773681640625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.389099657535553},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35217589139938354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33203941583633423},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2230701446533203},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21845698356628418},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12687960267066956},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09733647108078003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308750152587891},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6328549385070801},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6322473287582397},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5084985494613647},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4767773449420929},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45579278469085693},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45369720458984375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429245263338089},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.411773681640625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.389099657535553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35217589139938354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33203941583633423},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2230701446533203},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21845698356628418},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12687960267066956},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09733647108078003},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3533767.3534367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3533767.3534367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3533767.3534367","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3533767.3534367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3533767.3534367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3533767.3534367","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G5777954143","display_name":null,"funder_award_id":"61972224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7422924211","display_name":null,"funder_award_id":"BNR2022RC01006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285586654.pdf","grobid_xml":"https://content.openalex.org/works/W4285586654.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W200653874","https://openalex.org/W1690253345","https://openalex.org/W1942295288","https://openalex.org/W1967185446","https://openalex.org/W1974527629","https://openalex.org/W2009614414","https://openalex.org/W2012604743","https://openalex.org/W2024671287","https://openalex.org/W2068211976","https://openalex.org/W2096733369","https://openalex.org/W2157364932","https://openalex.org/W2439280908","https://openalex.org/W2516372287","https://openalex.org/W2532962075","https://openalex.org/W2547625248","https://openalex.org/W2559784535","https://openalex.org/W2577142429","https://openalex.org/W2579698096","https://openalex.org/W2596142952","https://openalex.org/W2597507805","https://openalex.org/W2602804099","https://openalex.org/W2602815560","https://openalex.org/W2611949786","https://openalex.org/W2618635610","https://openalex.org/W2625806818","https://openalex.org/W2627063456","https://openalex.org/W2749008552","https://openalex.org/W2768051178","https://openalex.org/W2806869036","https://openalex.org/W2886694146","https://openalex.org/W2888320512","https://openalex.org/W2888698761","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2945316254","https://openalex.org/W2963408280","https://openalex.org/W2963485370","https://openalex.org/W2997915791","https://openalex.org/W3007413911","https://openalex.org/W3010126799","https://openalex.org/W3011088748","https://openalex.org/W3105926539","https://openalex.org/W3127424491","https://openalex.org/W4236479165","https://openalex.org/W4244720976"],"related_works":["https://openalex.org/W3154635860","https://openalex.org/W3104152981","https://openalex.org/W4310420093","https://openalex.org/W4226332880","https://openalex.org/W2765199869","https://openalex.org/W1638297612","https://openalex.org/W2034043169","https://openalex.org/W3042939035","https://openalex.org/W2161708016","https://openalex.org/W200653874"],"abstract_inverted_index":{"Binary":[0],"code":[1,39,72],"similarity":[2],"detection":[3],"(BCSD)":[4],"has":[5],"important":[6],"applications":[7],"in":[8],"various":[9],"fields":[10],"such":[11],"as":[12],"vulnerabilities":[13],"detection,":[14],"software":[15],"component":[16],"analysis,":[17],"and":[18,40,87],"reverse":[19],"engineering.":[20],"Recent":[21],"studies":[22],"have":[23],"shown":[24],"that":[25,65,115,145],"deep":[26],"neural":[27],"networks":[28],"(DNNs)":[29],"can":[30],"comprehend":[31],"instructions":[32],"or":[33],"control-flow":[34],"graphs":[35],"(CFG)":[36],"of":[37,57,70,83,102,137],"binary":[38,58,71],"support":[41],"BCSD.":[42],"In":[43,133],"this":[44,122],"study,":[45],"we":[46,93],"propose":[47],"a":[48,79,88,98,134,143],"novel":[49,80],"Transformer-based":[50,74],"approach,":[51],"namely":[52],"jTrans,":[53],"to":[54,95,110,131],"learn":[55],"representations":[56],"code.":[59],"It":[60],"is":[61,106,146],"the":[62,84,96,107],"first":[63],"solution":[64],"embeds":[66],"control":[67],"flow":[68],"information":[69],"into":[73],"language":[75],"models,":[76],"by":[77,126],"using":[78],"jump-aware":[81],"representation":[82],"analyzed":[85],"binaries":[86],"newly-designed":[89],"pre-training":[90],"task.":[91],"Additionally,":[92],"release":[94],"community":[97],"newly-created":[99],"large":[100],"dataset":[101,125],"binaries,":[103],"BinaryCorp,":[104],"which":[105],"most":[108],"diverse":[109],"date.":[111],"Evaluation":[112],"results":[113],"show":[114],"jTrans":[116,141],"outperforms":[117],"state-of-the-art":[118],"(SOTA)":[119],"approaches":[120],"on":[121],"more":[123],"challenging":[124],"30.5%":[127],"(i.e.,":[128],"from":[129],"32.0%":[130],"62.5%).":[132],"real-world":[135],"task":[136],"known":[138],"vulnerability":[139],"searching,":[140],"achieves":[142],"recall":[144],"2X":[147],"higher":[148],"than":[149],"existing":[150],"SOTA":[151],"baselines.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":64},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}
