{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T04:04:18Z","timestamp":1775016258298,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T00:00:00Z","timestamp":1735171200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T00:00:00Z","timestamp":1735171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s10664-024-10605-x","type":"journal-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T11:45:06Z","timestamp":1735213506000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["OpTrans: enhancing binary code similarity detection with function inlining re-optimization"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1020-9006","authenticated-orcid":false,"given":"Zihan","family":"Sha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Shu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,26]]},"reference":[{"key":"10605_CR1","doi-asserted-by":"crossref","unstructured":"Liu B, Huo W, Zhang C, Li W, Li F, Piao A, Zou W (2018) $$\\alpha $$diff: Cross-version binary code similarity detection with dnn. In: Proceedings of the 33rd ACM\/IEEE international conference on automated software engineering, ASE 2018, Montpellier, France, September 3-7, 2018, pp 667\u2013678. ACM, New York, NY, USA","DOI":"10.1145\/3238147.3238199"},{"key":"10605_CR2","doi-asserted-by":"crossref","unstructured":"Zuo F, Li X, Zhang Z, Young P, Luo L, Zeng Q (2019) Neural machine translation inspired binary code similarity comparison beyond function pairs. In: 26th Annual network and distributed system security symposium, NDSS 2019, San Diego, California, USA, February 24-27, 2019","DOI":"10.14722\/ndss.2019.23492"},{"key":"10605_CR3","doi-asserted-by":"crossref","unstructured":"Ding SHH, Fung BCM, 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 2019, San Francisco, CA, USA, May 19-23, 2019, pp 472\u2013489","DOI":"10.1109\/SP.2019.00003"},{"key":"10605_CR4","doi-asserted-by":"crossref","unstructured":"Massarelli L, Luna GAD, Petroni F, Querzoni L, Baldoni R (2019) Safe: Self-attentive function embeddings for binary similarity. In: Detection of intrusions and malware, and vulnerability assessment - 16th international conference, DIMVA 2019, Gothenburg, Sweden, June 19-20, 2019, Proceedings. Lecture Notes in Computer Science, vol 11543, pp 309\u2013329","DOI":"10.1007\/978-3-030-22038-9_15"},{"key":"10605_CR5","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, pp 3236\u20133251","DOI":"10.1145\/3460120.3484587"},{"key":"10605_CR6","unstructured":"Li Y, Gu C, Dullien T, Vinyals O, Kohli P (2019) Graph matching networks for learning the similarity of graph structured objects. In: International conference on machine learning, PMLR, pp 3835\u20133845"},{"key":"10605_CR7","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. ISSTA \u201922: 31st ACM SIGSOFT International Symposium on Software Testing and Analysis. Virtual Event, South Korea, July 18\u201322, 2022. ACM, New York, NY, USA, pp 1\u201313","DOI":"10.1145\/3533767.3534367"},{"key":"10605_CR8","unstructured":"TensorFlow (2022) Word2vec skip-gram implementation in tensorflow. https:\/\/tensorflow.google.cn\/tutorials\/text\/word2vec"},{"key":"10605_CR9","doi-asserted-by":"crossref","unstructured":"Marhon SA, Cameron CJF, Kremer SC (2013) In: Bianchini M, Maggini M, Jain LC (eds) Recurrent Neural Networks, Springer, Berlin, Heidelberg, pp 29\u201365","DOI":"10.1007\/978-3-642-36657-4_2"},{"key":"10605_CR10","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"issue":"1","key":"10605_CR11","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Networks 20(1):61\u201380. https:\/\/doi.org\/10.1109\/TNN.2008.2005605","journal-title":"IEEE Trans Neural Networks"},{"key":"10605_CR12","doi-asserted-by":"crossref","unstructured":"Ji Y, Cui L, Huang HH (2021) Buggraph: Differentiating source-binary code similarity with graph triplet-loss network. ASIA CCS \u201921: ACM Asia Conference on Computer and Communications Security. Virtual Event, Hong Kong, June 7\u201311, 2021. ACM, New York, NY, USA, pp 702\u2013715","DOI":"10.1145\/3433210.3437533"},{"key":"10605_CR13","doi-asserted-by":"crossref","unstructured":"Xu X, Liu C, Feng Q, Yin H, Song L, Song DX (2017) Neural network-based graph embedding for cross-platform binary code similarity detection. In: Proceedings of the 2017 ACM SIGSAC conference on Computer and Communications Security, CCS 2017, Dallas, TX, USA, October 30 - November 03, 2017, pp 363\u2013376","DOI":"10.1145\/3133956.3134018"},{"key":"10605_CR14","doi-asserted-by":"crossref","unstructured":"Li X, Yu Q, Yin H (2021) Palmtree: Learning an assembly language model for instruction embedding. CCS \u201921: 2021 ACM SIGSAC Conference on Computer and Communications Security. Virtual Event, Republic of Korea, November 15\u201319, 2021. ACM, New York, NY, USA, pp 3236\u20133251","DOI":"10.1145\/3460120.3484587"},{"key":"10605_CR15","unstructured":"Project L (2024) Clang Documentation. Accessed on October 11, 2024. https:\/\/clang.llvm.org\/docs\/"},{"key":"10605_CR16","doi-asserted-by":"crossref","unstructured":"Cesare S, Xiang Y (2011) Malware variant detection using similarity search over sets of control flow graphs. In: IEEE 10th International conference on trust, security and privacy in computing and communications, TrustCom 2011, Changsha, China, 16-18 November, 2011, pp 181\u2013189","DOI":"10.1109\/TrustCom.2011.26"},{"key":"10605_CR17","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1109\/TDSC.2013.40","volume":"11","author":"S Cesare","year":"2014","unstructured":"Cesare S, Xiang Y, Zhou W (2014) Control flow-based malware variantdetection. IEEE Trans Dependable Secure Comput 11:307\u2013317","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"10605_CR18","doi-asserted-by":"crossref","unstructured":"Tam\u00e1s C, Papp D, Butty\u00e1n L (2021) Simbiota: Similarity-based malware detection on iot devices. In: Proceedings of the 6th International Conference on Internet of Things, Big Data and Security, IoTBDS 2021, Online Streaming, April 23-25, 2021, pp 58\u201369","DOI":"10.5220\/0010441500580069"},{"key":"10605_CR19","doi-asserted-by":"crossref","unstructured":"Hu Y, Zhang Y, Li J, Gu D (2017) Binary code clone detection across architectures and compiling configurations. In: Proceedings of the 25th International Conference on Program Comprehension, ICPC 2017, Buenos Aires, Argentina, May 22-23, 2017, pp 88\u201398","DOI":"10.1109\/ICPC.2017.22"},{"key":"10605_CR20","doi-asserted-by":"crossref","unstructured":"Ding SHH, Fung BCM, Charland P (2016) Kam1n0: Mapreduce-based assembly clone search for reverse engineering. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016, pp 461\u2013470","DOI":"10.1145\/2939672.2939719"},{"key":"10605_CR21","doi-asserted-by":"crossref","unstructured":"Xu Z, Chen B, Chandramohan M, Liu Y, Song F (2017) Spain: Security patch analysis for binaries towards understanding the pain and pills. In: Proceedings of the 39th International Conference on Software Engineering, ICSE 2017, Buenos Aires, Argentina, May 20-28, 2017, pp 462\u2013472","DOI":"10.1109\/ICSE.2017.49"},{"key":"10605_CR22","doi-asserted-by":"crossref","unstructured":"Gao D, Reiter MK, Song DX (2008) Binhunt: Automatically finding semantic differences in binary programs. In: Information and Communications Security, 10th International Conference, ICICS 2008, Birmingham, UK, October 20-22, 2008, Proceedings. Lecture Notes in Computer Science, vol 5308, pp 238\u2013255","DOI":"10.1007\/978-3-540-88625-9_16"},{"key":"10605_CR23","doi-asserted-by":"crossref","unstructured":"Chandramohan M, Xue Y, Xu Z, Liu Y, Cho CY, Tan HBK (2016) Bingo: cross-architecture cross-os binary search. In: Proceedings of the 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering, FSE 2016, Seattle, WA, USA, November 13-18, 2016, pp 678\u2013689","DOI":"10.1145\/2950290.2950350"},{"key":"10605_CR24","first-page":"83","volume":"59","author":"J Pewny","year":"2015","unstructured":"Pewny J, Garmany B, Gawlik R, Rossow C, Holz T (2015) Cross-architecture bug search in binary executables. Inf Technol 59:83\u201391","journal-title":"Inf Technol"},{"key":"10605_CR25","unstructured":"Hex-rays (2022) Ida pro disassembler and debugger. https:\/\/www.hex-rays.com\/products\/ida\/index.shtml"},{"key":"10605_CR26","unstructured":"Dullien T, Rolles R (2005) Graph-based comparison of executable objects (english version). In: SSTIC, vol 5, p 3"},{"key":"10605_CR27","doi-asserted-by":"crossref","unstructured":"Eschweiler S, Yakdan K, Gerhards-Padilla E (2016) discovre: Efficient cross-architecture identification of bugs in binary code. In: 23rd Annual Network and Distributed System Security Symposium, NDSS 2016, San Diego, California, USA, February 21-24, 2016","DOI":"10.14722\/ndss.2016.23185"},{"key":"10605_CR28","doi-asserted-by":"crossref","unstructured":"Pewny J, Schuster F, Bernhard L, Holz T, Rossow C (2014) Leveraging semantic signatures for bug search in binary programs. In: Proceedings of the 30th Annual Computer Security Applications Conference, ACSAC 2014, New Orleans, LA, USA, December 8-12, 2014, pp 406\u2013415","DOI":"10.1145\/2664243.2664269"},{"key":"10605_CR29","doi-asserted-by":"crossref","unstructured":"Feng Q, Zhou R, Xu C, Cheng Y, Testa B, Yin H (2016) Scalable graph-based bug search for firmware images. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria, October 24-28, 2016, pp 480\u2013491. ACM, New York, NY, USA","DOI":"10.1145\/2976749.2978370"},{"key":"10605_CR30","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a Meeting Held December 5-8, 2013, Lake Tahoe, Nevada, United States, pp 3111\u20133119"},{"key":"10605_CR31","unstructured":"He H, Lin X, Weng Z, Zhao R, Gan S, Chen L, Ji Y, Wang J, Xue Z (2024) Code is not natural language: Unlock the power of Semantics-Oriented graph representation for binary code similarity detection. In: 33rd USENIX Security Symposium (USENIX Security 24), pp 1759\u20131776. USENIX Association, Philadelphia, PA. https:\/\/www.usenix.org\/conference\/usenixsecurity24\/presentation\/he-haojie"},{"key":"10605_CR32","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. Proceedings 2023 Network and Distributed System Security Symposium","DOI":"10.14722\/ndss.2023.24415"},{"key":"10605_CR33","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"10605_CR34","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR)"},{"key":"10605_CR35","doi-asserted-by":"crossref","unstructured":"Yang S, Dong C, Xiao Y, Cheng Y, Shi Z, Li Z, Sun L (2023) Asteria-pro: enhancing deep-learning based binary code similarity detection by incorporating domain knowledge. ACM Trans Softw Eng Methodology","DOI":"10.1145\/3604611"},{"key":"10605_CR36","doi-asserted-by":"publisher","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(4). https:\/\/doi.org\/10.1145\/3561385","DOI":"10.1145\/3561385"},{"key":"10605_CR37","doi-asserted-by":"publisher","unstructured":"Jia A, Fan M, Xu X, Jin W, Wang H, Liu T (2024) Cross-inlining binary function similarity detection. In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. ICSE \u201924. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3597503.3639080","DOI":"10.1145\/3597503.3639080"},{"key":"10605_CR38","doi-asserted-by":"crossref","unstructured":"Jin X, Pei K, Won JY, 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, pp 1631\u20131645","DOI":"10.1145\/3548606.3560612"},{"key":"10605_CR39","doi-asserted-by":"crossref","unstructured":"Patrick-Evans J, Dannehl M, Kinder J (2023) Xfl: naming functions in binaries with extreme multi-label learning. In: 2023 IEEE Symposium on Security and Privacy (SP), IEEE, pp 2375\u20132390","DOI":"10.1109\/SP46215.2023.10179439"},{"issue":"6","key":"10605_CR40","doi-asserted-by":"publisher","first-page":"4156","DOI":"10.1109\/TDSC.2021.3123159","volume":"19","author":"Z Sha","year":"2022","unstructured":"Sha Z, Shu H, Xiong X, Kang F (2022) Model of execution trace obfuscation between threads. IEEE Trans Dependable Secure Comput 19(6):4156\u20134171. https:\/\/doi.org\/10.1109\/TDSC.2021.3123159","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"10605_CR41","unstructured":"Hex-Rays. (2021) IDA Pro Disassembler and Debugger. Retrieved September 10, 2023 from http:\/\/www.hex-rays.com\/products\/ida\/index.shtml"},{"key":"10605_CR42","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: An imperative style, high-performance deep learning library. Advan Neural Inf Process Syst 32"},{"key":"10605_CR43","doi-asserted-by":"crossref","unstructured":"Wang H, Gao Z, Zhang C, Sha Z, Sun M, Zhou Y, Zhu W, Sun W, Qiu H, Xiao X (2024) CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision","DOI":"10.1145\/3650212.3652145"},{"key":"10605_CR44","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. CoRR arXiv:1412.6980"},{"key":"10605_CR45","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11)"},{"key":"10605_CR46","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, pp 1\u201313","DOI":"10.1145\/3533767.3534367"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10605-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-024-10605-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10605-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:45:17Z","timestamp":1746193517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-024-10605-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,26]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10605"],"URL":"https:\/\/doi.org\/10.1007\/s10664-024-10605-x","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,26]]},"assertion":[{"value":"10 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that all authors have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest Statement"}}],"article-number":"49"}}