{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T18:48:46Z","timestamp":1785350926509,"version":"3.55.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Communication-Oriented AI Security: Core Technology Development and System Implementation","award":["CUCAI24004"],"award-info":[{"award-number":["CUCAI24004"]}]},{"name":"Communication-Oriented AI Security: Core Technology Development and System Implementation","award":["CUCAI24004"],"award-info":[{"award-number":["CUCAI24004"]}]},{"name":"Communication-Oriented AI Security: Core Technology Development and System Implementation","award":["CUCAI24004"],"award-info":[{"award-number":["CUCAI24004"]}]},{"name":"Communication-Oriented AI Security: Core Technology Development and System Implementation","award":["CUCAI24004"],"award-info":[{"award-number":["CUCAI24004"]}]},{"name":"Communication-Oriented AI Security: Core Technology Development and System Implementation","award":["CUCAI24004"],"award-info":[{"award-number":["CUCAI24004"]}]},{"name":"Communication-Oriented AI Security: Core Technology Development and System Implementation","award":["CUCAI24004"],"award-info":[{"award-number":["CUCAI24004"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07895-3","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T16:46:25Z","timestamp":1759509985000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CrossSimEmb: transformer-based embedding model for cross-compilation binary code similarity detection"],"prefix":"10.1007","volume":"81","author":[{"given":"Gaoqing","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuyang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aina","family":"Sui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"7895_CR1","doi-asserted-by":"publisher","first-page":"114348","DOI":"10.1016\/j.eswa.2020.114348","volume":"168","author":"D Tian","year":"2021","unstructured":"Tian D, Jia X, Ma R, Liu S, Liu W, Hu C (2021) Bindeep: a deep learning approach to binary code similarity detection. Expert Syst Appl 168:114348","journal-title":"Expert Syst Appl"},{"key":"7895_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3561385","volume":"32","author":"A Jia","year":"2023","unstructured":"Jia A, Fan M, Jin W, Xu X, Zhou Z, Tang Q, Nie S, Wu S, Liu T (2023) 1-to-1 or 1-to-n? investigating the effect of function inlining on binary similarity analysis. ACM Trans Softw Eng Methodol 32:1\u201326","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"7895_CR3","doi-asserted-by":"crossref","unstructured":"Liu X, Wu Y, Yu Q, Song S, Liu Y, Zhou Q, Zhuge, J (2022) PG-VulNet: detect supply chain vulnerabilities in IoT devices using pseudo-code and graphs. In: Proceedings of the 16th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement, 205\u2013215","DOI":"10.1145\/3544902.3546240"},{"key":"7895_CR4","doi-asserted-by":"crossref","unstructured":"Duan Y, Li X, Wang J, Yin H (2020) Others Deepbindiff: learning program-wide code representations for binary diffing","DOI":"10.14722\/ndss.2020.24311"},{"key":"7895_CR5","doi-asserted-by":"publisher","first-page":"103023","DOI":"10.1016\/j.cose.2022.103023","volume":"125","author":"Y Wang","year":"2023","unstructured":"Wang Y, Jia P, Peng X, Huang C, Liu J (2023) Binvuldet: detecting vulnerability in binary program via decompiled pseudo code and bilstm-attention. Comput Secur 125:103023","journal-title":"Comput Secur"},{"key":"7895_CR6","first-page":"1","volume":"33","author":"S Li","year":"2023","unstructured":"Li S, Wang Y, Dong C, Yang S, Li H, Sun H, Lang Z, Chen Z, Wang W, Zhu H (2023) Others Libam: an area matching framework for detecting third-party libraries in binaries. ACM Trans Softw Eng Methodol 33:1\u201335","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"7895_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s42400-021-00085-7","volume":"4","author":"G Ban","year":"2021","unstructured":"Ban G, Xu L, Xiao Y, Li X, Yuan Z, Huo W (2021) B2smatcher: fine-grained version identification of open-source software in binary files. Cybersecurity 4:21","journal-title":"Cybersecurity"},{"key":"7895_CR8","doi-asserted-by":"crossref","unstructured":"Xu Y, Xu Z, Chen B, Song F, Liu Y, Liu T (2020) Patch based vulnerability matching for binary programs. In: Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis, 376\u2013387","DOI":"10.1145\/3395363.3397361"},{"key":"7895_CR9","unstructured":"Miyani D, Huang Z, Lie D (2017) Binpro: a tool for binary source code provenance. ArXiv Preprint arXiv:1711.00830"},{"key":"7895_CR10","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1109\/TSE.2021.3056139","volume":"48","author":"J Yang","year":"2021","unstructured":"Yang J, Fu C, Liu X, Yin H, Zhou P (2021) Codee: a tensor embedding scheme for binary code search. IEEE Trans Softw Eng 48:2224\u20132244","journal-title":"IEEE Trans Softw Eng"},{"key":"7895_CR11","doi-asserted-by":"crossref","unstructured":"Liu Z, Zhang Z, Ma S, Liu D, Zhang J, Chen C, Liu S, Ahmed M, Xiang Y (2023) Semdiff: binary similarity detection by diffing key-semantics graphs. ArXiv Preprint arXiv:2308.01463","DOI":"10.2139\/ssrn.4459331"},{"key":"7895_CR12","doi-asserted-by":"crossref","unstructured":"Cao Y, Liang R, Chen K, Hu P (2022) Boosting neural networks to decompile optimized binaries. In: Proceedings of the 38th Annual Computer Security Applications Conference, 508\u2013518","DOI":"10.1145\/3564625.3567998"},{"key":"7895_CR13","doi-asserted-by":"crossref","unstructured":"Kim G, Hong S, Franz M, Song D (2022) Improving cross-platform binary analysis using representation learning via graph alignment. In: Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, 151\u2013163","DOI":"10.1145\/3533767.3534383"},{"key":"7895_CR14","doi-asserted-by":"crossref","unstructured":"Al-Kaswan A, Ahmed T, Izadi M, Sawant A, Devanbu P, Deursen A (2023) Extending source code pre-trained language models to summarise decompiled binaries. In: 2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 260\u2013271","DOI":"10.1109\/SANER56733.2023.00033"},{"key":"7895_CR15","doi-asserted-by":"crossref","unstructured":"Gao L, Qu Y, Yu S, Duan Y, Yin H (Internet Society, 2024) SigmaDiff: semantics-aware deep graph matching for pseudocode diffing","DOI":"10.14722\/ndss.2024.23208"},{"key":"7895_CR16","doi-asserted-by":"publisher","first-page":"7789","DOI":"10.3390\/s23187789","volume":"23","author":"Z Luo","year":"2023","unstructured":"Luo Z, Wang P, Xie W, Zhou X, Wang B (2023) Iotsim: internet of things-oriented binary code similarity detection with multiple block relations. Sensors 23:7789","journal-title":"Sensors"},{"key":"7895_CR17","unstructured":"Pei K, Xuan Z, Yang J, Jana S, Ray B (2020) Trex: learning execution semantics from micro-traces for binary similarity. ArXiv Preprint arXiv:2012.08680"},{"key":"7895_CR18","unstructured":"Alon U, Brody S, Levy O, Yahav E (2018) code2seq: generating sequences from structured representations of code. ArXiv Preprint arXiv:1808.01400"},{"key":"7895_CR19","doi-asserted-by":"crossref","unstructured":"Zhang J, Wang X, Zhang H, Sun H, Liu X (2020) Retrieval-based neural source code summarization. In: Proceedings Of The ACM\/IEEE 42nd International Conference on Software Engineering, 1385\u20131397","DOI":"10.1145\/3377811.3380383"},{"key":"7895_CR20","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1109\/TSE.2019.2956932","volume":"47","author":"J Gao","year":"2019","unstructured":"Gao J, Jiang Y, Liu Z, Yang X, Wang C, Jiao X, Yang Z, Sun J (2019) Semantic learning and emulation based cross-platform binary vulnerability seeker. IEEE Trans Softw Eng 47:2575\u20132589","journal-title":"IEEE Trans Softw Eng"},{"key":"7895_CR21","unstructured":"Zhu W, Wang H, Zhou Y, Wang J, Sha Z, Gao Z, Zhang C (2023) ktrans: knowledge-aware transformer for binary code embedding. ArXiv Preprint arXiv:2308.12659"},{"key":"7895_CR22","doi-asserted-by":"crossref","unstructured":"Wang Y, Le H, Gotmare A, Bui N, Li J, Hoi S (2023) Codet5+: open code large language models for code understanding and generation. ArXiv Preprint arXiv:2305.07922","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"7895_CR23","doi-asserted-by":"crossref","unstructured":"Pei K, Guan J, Williams-King D, Yang J, Jana S (2020) Xda: accurate, robust disassembly with transfer learning. ArXiv Preprint arXiv:2010.00770","DOI":"10.14722\/ndss.2021.23112"},{"key":"7895_CR24","unstructured":"Szafraniec M, Roziere B, Leather H, Charton F, Labatut P, Synnaeve G (2022) Code translation with compiler representations. ArXiv Preprint arXiv:2207.03578"},{"key":"7895_CR25","doi-asserted-by":"crossref","unstructured":"Geng H, Zhong M, Zhang P, Lv F, Feng X (2023) OPTango: multi-central representation learning against innumerable compiler optimization for binary diffing. In: 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE), 774\u2013785","DOI":"10.1109\/ISSRE59848.2023.00013"},{"key":"7895_CR26","doi-asserted-by":"crossref","unstructured":"Luo Z, Wang P, Wang B, Tang Y, Xie W, Zhou X, Liu D, Lu K (2023) VulHawk: cross-architecture vulnerability detection with entropy-based binary code search. NDSS","DOI":"10.14722\/ndss.2023.24415"},{"key":"7895_CR27","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang Y, Liu Y, Pang Z, Fang B (2022) PDG2Vec: identify the binary function similarity with program dependence graph. In: 2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS), 537\u2013548","DOI":"10.1109\/QRS57517.2022.00061"},{"key":"7895_CR28","doi-asserted-by":"crossref","unstructured":"Zuo F, Li X, Young P, Luo L, Zeng Q, Zhang Z (2018) Neural machine translation inspired binary code similarity comparison beyond function pairs. ArXiv Preprint arXiv:1808.04706","DOI":"10.14722\/ndss.2019.23492"},{"key":"7895_CR29","doi-asserted-by":"crossref","unstructured":"Ding S, Fung B, Charland P (2019) Asm2vec: boosting static representation robustness for binary clone search against code obfuscation and compiler optimization. In: 2019 IEEE Symposium on Security and Privacy (sp)., 472\u2013489","DOI":"10.1109\/SP.2019.00003"},{"key":"7895_CR30","doi-asserted-by":"publisher","first-page":"4528","DOI":"10.3934\/mbe.2021230","volume":"18","author":"X Zhu","year":"2021","unstructured":"Zhu X, Jiang L, Chen Z (2021) Cross-platform binary code similarity detection based on nmt and graph embedding. Math Biosci Eng 18:4528\u20134551","journal-title":"Math Biosci Eng"},{"key":"7895_CR31","doi-asserted-by":"publisher","first-page":"12751","DOI":"10.3390\/app132312751","volume":"13","author":"Z Luo","year":"2023","unstructured":"Luo Z, Wang P, Xie W, Zhou X, Wang B (2023) Blockmatch: a fine-grained binary code similarity detection approach using contrastive learning for basic block matching. Appl Sci 13:12751","journal-title":"Appl Sci"},{"key":"7895_CR32","doi-asserted-by":"crossref","unstructured":"Li L, Ding S, Charland P (2023) GenTAL: generative denoising skip-gram transformer for unsupervised binary code similarity detection. In: 2023 International Joint Conference on Neural Networks (IJCNN), 1\u20138","DOI":"10.1109\/IJCNN54540.2023.10191550"},{"key":"7895_CR33","doi-asserted-by":"crossref","unstructured":"Wang H, Gao Z, Zhang C, Sun M, Zhou Y, Qiu H, Xiao X (2024) Cebin: a cost-effective framework for large-scale binary code similarity detection. In: Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, 149\u2013161","DOI":"10.1145\/3650212.3652117"},{"key":"7895_CR34","unstructured":"Koo H, Park S, Choi D, Kim T (2021) Semantic-aware binary code representation with bert. ArXiv Preprint arXiv:2106.05478"},{"key":"7895_CR35","doi-asserted-by":"crossref","unstructured":"Wang H, Qu W, Katz G, Zhu W, Gao Z, Qiu H, Zhuge J, Zhang C (2022) Jtrans: jump-aware transformer for binary code similarity detection. In: Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, 1\u201313","DOI":"10.1145\/3533767.3534367"},{"key":"7895_CR36","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s44196-023-00206-9","volume":"16","author":"J Guo","year":"2023","unstructured":"Guo J, Zhao B, Liu H, Leng D, An Y, Shu G (2023) Deepdual-sd: deep dual attribute-aware embedding for binary code similarity detection. Int J Comput Intell Syst 16:35","journal-title":"Int J Comput Intell Syst"},{"key":"7895_CR37","doi-asserted-by":"publisher","first-page":"2549","DOI":"10.3390\/sym14122549","volume":"14","author":"H Gao","year":"2022","unstructured":"Gao H, Zhang T, Chen S, Wang L, Yu F (2022) Fusion: measuring binary function similarity with code-specific embedding and order-sensitive gnn. Symmetry 14:2549","journal-title":"Symmetry"},{"key":"7895_CR38","doi-asserted-by":"crossref","unstructured":"Guo Y, Li P, Luo Y, Wang X, Wang Z (2022) Exploring gnn based program embedding technologies for binary related tasks. In: Proceedings of the 30th IEEE\/ACM International Conference on Program Comprehension, 366\u2013377","DOI":"10.1145\/3524610.3527900"},{"key":"7895_CR39","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s10664-024-10593-y","volume":"30","author":"Z Sha","year":"2025","unstructured":"Sha Z, Zhang C, Wang H, Gao Z, Zhang B, Lan Y, Shu H (2025) Prometrans: bootstrap binary functionality classification with knowledge transferred from pre-trained models. Empir Softw Eng 30:32","journal-title":"Empir Softw Eng"},{"key":"7895_CR40","unstructured":"Wang X, Wang J, Su J, Wang K, Chen P, Liu Y, Liu L, Li X, Wang Y, Chen Q (2025) Others ASMA-Tune: unlocking LLMs\u2019 assembly code comprehension via structural-semantic instruction tuning. ArXiv Preprint arXiv:2503.11617"},{"key":"7895_CR41","doi-asserted-by":"crossref","unstructured":"Ahn S, Ahn S, Koo H, Paek Y (2022) Practical binary code similarity detection with bert-based transferable similarity learning. In: Proceedings of the 38th Annual Computer Security Applications Conference, 361\u2013374","DOI":"10.1145\/3564625.3567975"},{"key":"7895_CR42","doi-asserted-by":"publisher","first-page":"102804","DOI":"10.1016\/j.cose.2022.102804","volume":"120","author":"S Jiang","year":"2022","unstructured":"Jiang S, Fu C, Qian Y, He S, Lv J, Han L (2022) Ifattn: binary code similarity analysis based on interpretable features with attention. Comput Secur 120:102804","journal-title":"Comput Secur"},{"key":"7895_CR43","doi-asserted-by":"crossref","unstructured":"Gui Y, Wan Y, Zhang H, Huang H, Sui Y, Xu G, Shao Z, Jin H (2022) Cross-language binary-source code matching with intermediate representations. In: 2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 601\u2013612","DOI":"10.1109\/SANER53432.2022.00077"},{"key":"7895_CR44","unstructured":"Peng D, Zheng S, Li Y, Ke G, He D, Liu T (2021) How could neural networks understand programs?. In: International Conference on Machine Learning, 8476\u20138486"},{"key":"7895_CR45","doi-asserted-by":"crossref","unstructured":"Li X, Qu Y, Yin H (2021) Palmtree: learning an assembly language model for instruction embedding. In: Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 3236\u20133251","DOI":"10.1145\/3460120.3484587"},{"key":"7895_CR46","doi-asserted-by":"crossref","unstructured":"Jin X, Pei K, Won J, Lin Z (2022) Symlm: predicting function names in stripped binaries via context-sensitive execution-aware code embeddings. In: Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 1631\u20131645","DOI":"10.1145\/3548606.3560612"},{"key":"7895_CR47","doi-asserted-by":"crossref","unstructured":"Xu X, Feng S, Ye Y, Shen G, Su Z, Cheng S, Tao G, Shi Q, Zhang Z, Zhang X (2023) Improving binary code similarity transformer models by semantics-driven instruction deemphasis. In: Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, 1106\u20131118","DOI":"10.1145\/3597926.3598121"},{"key":"7895_CR48","unstructured":"Marcelli A, Graziano M, Ugarte-Pedrero X, Fratantonio Y, Mansouri M, Balzarotti D (2022) How machine learning is solving the binary function similarity problem. In: 31st USENIX Security Symposium (USENIX Security 22), 2099\u20132116"},{"key":"7895_CR49","doi-asserted-by":"crossref","unstructured":"Kendall A, Gal Y, Cipolla R (2018) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7482\u20137491","DOI":"10.1109\/CVPR.2018.00781"},{"key":"7895_CR50","doi-asserted-by":"publisher","first-page":"129238","DOI":"10.1016\/j.neucom.2024.129238","volume":"620","author":"G Yu","year":"2025","unstructured":"Yu G, An J, Lyu J, Huang W, Fan W, Cheng Y, Sui A (2025) Crosscode2vec: a unified representation across source and binary functions for code similarity detection. Neurocomputing 620:129238","journal-title":"Neurocomputing"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07895-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07895-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07895-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T16:46:34Z","timestamp":1759509994000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07895-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":50,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["7895"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07895-3","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"16 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1405"}}