{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T04:13:56Z","timestamp":1781064836902,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:00:00Z","timestamp":1726012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"DOI":"10.1145\/3650212.3652117","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:44:25Z","timestamp":1726055065000},"page":"149-161","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-5039","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2318-9061","authenticated-orcid":false,"given":"Zeyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7894-8828","authenticated-orcid":false,"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7858-9246","authenticated-orcid":false,"given":"Mingyang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7021-1183","authenticated-orcid":false,"given":"Yuchen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2678-8070","authenticated-orcid":false,"given":"Han","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1521-9542","authenticated-orcid":false,"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3564625.3567975"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3564625.3567975"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3175492"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2013.40"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980983.2908126"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3062341.3062387"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3177157"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2666356.2594343"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00003"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.24311"},{"key":"e_1_3_2_1_11_1","first-page":"3","article-title":"Graph-based comparison of executable objects (english version)","volume":"5","author":"Dullien Thomas","year":"2005","unstructured":"Thomas Dullien and Rolf Rolles. 2005. Graph-based comparison of executable objects (english version). Sstic, 5, 1 (2005), 3.","journal-title":"Sstic"},{"key":"e_1_3_2_1_12_1","first-page":"58","article-title":"discovRE: Efficient Cross-Architecture Identification of Bugs in Binary Code","volume":"52","author":"Eschweiler Sebastian","year":"2016","unstructured":"Sebastian Eschweiler, Khaled Yakdan, and Elmar Gerhards-Padilla. 2016. discovRE: Efficient Cross-Architecture Identification of Bugs in Binary Code.. In NDSS. 52, 58\u201379.","journal-title":"NDSS."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SERE.2014.21"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3052995"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978370"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88625-9_16"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3240480"},{"key":"e_1_3_2_1_18_1","unstructured":"Zeyu Gao Hao Wang Yuchen Zhou Wenyu Zhu and Chao Zhang. 2023. How Far Have We Gone in Vulnerability Detection Using Large Language Models. arxiv:2311.12420."},{"key":"e_1_3_2_1_19_1","unstructured":"Haojie He Xingwei Lin Ziang Weng Ruijie Zhao Shuitao Gan Libo Chen Yuede Ji Jiashui Wang and Zhi Xue. [n. d.]. Code is not Natural Language: Unlock the Power of Semantics-Oriented Graph Representation for Binary Code Similarity Detection."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_21_1","volume-title":"Mutantx-s: Scalable malware clustering based on static features. In 2013 $USENIX$ Annual Technical Conference ($USENIX$$ATC$ 13). 187\u2013198.","author":"Hu Xin","year":"2013","unstructured":"Xin Hu, Kang G Shin, Sandeep Bhatkar, and Kent Griffin. 2013. Mutantx-s: Scalable malware clustering based on static features. In 2013 $USENIX$ Annual Technical Conference ($USENIX$$ATC$ 13). 187\u2013198."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2016.50"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3052974"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2012.13"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Ling Jiang Junwen An Huihui Huang Qiyi Tang Sen Nie Shi Wu and Yuqun Zhang. 2024. BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matching. arxiv:2401.11161.","DOI":"10.1145\/3597503.3639100"},{"key":"e_1_3_2_1_26_1","unstructured":"Nan Jiang Chengxiao Wang Kevin Liu Xiangzhe Xu Lin Tan and Xiangyu Zhang. 2023. Nova^+: Generative Language Models for Binaries. arxiv:2311.13721."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115647"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1941-2"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Taku Kudo. 2018. Subword regularization: Improving neural network translation models with multiple subword candidates. arXiv preprint arXiv:1804.10959.","DOI":"10.18653\/v1\/P18-1007"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_32_1","first-page":"1","article-title":"Libam: An area matching framework for detecting third-party libraries in binaries","volume":"33","author":"Li Siyuan","year":"2023","unstructured":"Siyuan Li, Yongpan Wang, Chaopeng Dong, Shouguo Yang, Hong Li, Hao Sun, Zhe Lang, Zuxin Chen, Weijie Wang, and Hongsong Zhu. 2023. Libam: An area matching framework for detecting third-party libraries in binaries. ACM Transactions on Software Engineering and Methodology, 33, 2 (2023), 1\u201335.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484587"},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. 3835\u20133845","author":"Li Yujia","year":"2019","unstructured":"Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, and Pushmeet Kohli. 2019. Graph matching networks for learning the similarity of graph structured objects. In International conference on machine learning. 3835\u20133845."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238199"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2635868.2635900"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2655046"},{"key":"e_1_3_2_1_38_1","volume-title":"VulHawk: Cross-architecture Vulnerability Detection with Entropy-based Binary Code Search. In 30th Annual Network and Distributed System Security Symposium, NDSS 2023","author":"Luo Zhenhao","year":"2023","unstructured":"Zhenhao Luo, Pengfei Wang, Baosheng Wang, Yong Tang, Wei Xie, Xu Zhou, Danjun Liu, and Kai Lu. 2023. VulHawk: Cross-architecture Vulnerability Detection with Entropy-based Binary Code Search. In 30th Annual Network and Distributed System Security Symposium, NDSS 2023, San Diego, California, USA, February 27 - March 3, 2023. The Internet Society. https:\/\/www.ndss-symposium.org\/ndss-paper\/vulhawk-cross-architecture-vulnerability-detection-with-entropy-based-binary-code-search\/"},{"key":"e_1_3_2_1_39_1","volume-title":"How Machine Learning Is Solving the Binary Function Similarity Problem. In 31st USENIX Security Symposium (USENIX Security 22)","author":"Marcelli Andrea","year":"2022","unstructured":"Andrea Marcelli, Mariano Graziano, Xabier Ugarte-Pedrero, Yanick Fratantonio, Mohamad Mansouri, and Davide Balzarotti. 2022. How Machine Learning Is Solving the Binary Function Similarity Problem. In 31st USENIX Security Symposium (USENIX Security 22). USENIX Association, Boston, MA. 2099\u20132116. isbn:978-1-939133-31-1 https:\/\/www.usenix.org\/conference\/usenixsecurity22\/presentation\/marcelli"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22038-9_15"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14722\/bar.2019.23020"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58469-0_23"},{"key":"e_1_3_2_1_43_1","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748."},{"key":"e_1_3_2_1_44_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_45_1","volume-title":"Trex: Learning execution semantics from micro-traces for binary similarity. arXiv preprint arXiv:2012.08680.","author":"Pei Kexin","year":"2020","unstructured":"Kexin Pei, Zhou Xuan, Junfeng Yang, Suman Jana, and Baishakhi Ray. 2020. Trex: Learning execution semantics from micro-traces for binary similarity. arXiv preprint arXiv:2012.08680."},{"key":"e_1_3_2_1_46_1","article-title":"Learning Approximate Execution Semantics From Traces for Binary Function Similarity","author":"Pei Kexin","year":"2022","unstructured":"Kexin Pei, Zhou Xuan, Junfeng Yang, Suman Jana, and Baishakhi Ray. 2022. Learning Approximate Execution Semantics From Traces for Binary Function Similarity. IEEE Transactions on Software Engineering.","journal-title":"IEEE Transactions on Software Engineering."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.49"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2664243.2664269"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579856.3582818"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Kimberly Redmond Lannan Luo and Qiang Zeng. 2018. A cross-architecture instruction embedding model for natural language processing-inspired binary code analysis. arXiv preprint arXiv:1812.09652.","DOI":"10.14722\/bar.2019.23057"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3264820.3264821"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3264820.3264821"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93411-2_6"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054845"},{"key":"e_1_3_2_1_55_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30 (2017)."},{"key":"e_1_3_2_1_56_1","volume-title":"CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision. arxiv:2402.16928.","author":"Wang Hao","year":"2024","unstructured":"Hao Wang, Zeyu Gao, Chao Zhang, Zihan Sha, Mingyang Sun, Yuchen Zhou, Wenyu Zhu, Wenju Sun, Han Qiu, and Xi Xiao. 2024. CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision. arxiv:2402.16928."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3149240"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Hao Wang Wenjie Qu Gilad Katz Wenyu Zhu Zeyu Gao Han Qiu Jianwei Zhuge and Chao Zhang. 2022. jTrans: Jump-Aware Transformer for Binary Code Similarity. arXiv preprint arXiv:2205.12713.","DOI":"10.1145\/3533767.3534367"},{"key":"e_1_3_2_1_59_1","volume-title":"COSEA: Convolutional Code Search with Layer-wise Attention. arxiv:2010.09520.","author":"Wang Hao","year":"2020","unstructured":"Hao Wang, Jia Zhang, Yingce Xia, Jiang Bian, Chao Zhang, and Tie-Yan Liu. 2020. COSEA: Convolutional Code Search with Layer-wise Attention. arxiv:2010.09520."},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis. 1106\u20131118","author":"Xu Xiangzhe","year":"2023","unstructured":"Xiangzhe Xu, Shiwei Feng, Yapeng Ye, Guangyu Shen, Zian Su, Siyuan Cheng, Guanhong Tao, Qingkai Shi, Zhuo Zhang, and Xiangyu Zhang. 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."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598121"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134018"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.49"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3056139"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3604611","article-title":"Asteria-Pro: Enhancing Deep Learning-based Binary Code Similarity Detection by Incorporating Domain Knowledge","volume":"33","author":"Yang Shouguo","year":"2023","unstructured":"Shouguo Yang, Chaopeng Dong, Yang Xiao, Yiran Cheng, Zhiqiang Shi, Zhi Li, and Limin Sun. 2023. Asteria-Pro: Enhancing Deep Learning-based Binary Code Similarity Detection by Incorporating Domain Knowledge. ACM Transactions on Software Engineering and Methodology, 33, 1 (2023), 1\u201340.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5466"},{"key":"e_1_3_2_1_67_1","first-page":"3872","article-title":"Codecmr: Cross-modal retrieval for function-level binary source code matching","volume":"33","author":"Yu Zeping","year":"2020","unstructured":"Zeping Yu, Wenxin Zheng, Jiaqi Wang, Qiyi Tang, Sen Nie, and Shi Wu. 2020. Codecmr: Cross-modal retrieval for function-level binary source code matching. Advances in Neural Information Processing Systems, 33 (2020), 3872\u20133883.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_68_1","unstructured":"Wenyu Zhu Hao Wang Yuchen Zhou Jiaming Wang Zihan Sha Zeyu Gao and Chao Zhang. 2023. kTrans: Knowledge-Aware Transformer for Binary Code Embedding. arxiv:2308.12659."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13010413"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Fei Zuo Xiaopeng Li Patrick Young Lannan Luo Qiang Zeng and Zhexin Zhang. 2018. Neural machine translation inspired binary code similarity comparison beyond function pairs. arXiv preprint arXiv:1808.04706.","DOI":"10.14722\/ndss.2019.23492"},{"key":"e_1_3_2_1_71_1","unstructured":"zynamics. 2018. BinDiff. \"https:\/\/www.zynamics.com\/bindiff.html\""}],"event":{"name":"ISSTA '24: 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","location":"Vienna Austria","acronym":"ISSTA '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","AITO"]},"container-title":["Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3652117","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650212.3652117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:06Z","timestamp":1750287006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3652117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":71,"alternative-id":["10.1145\/3650212.3652117","10.1145\/3650212"],"URL":"https:\/\/doi.org\/10.1145\/3650212.3652117","relation":{},"subject":[],"published":{"date-parts":[[2024,9,11]]},"assertion":[{"value":"2024-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}