{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:43:37Z","timestamp":1785512617802,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639100","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3134-1811","authenticated-orcid":false,"given":"Ling","family":"Jiang","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1768-7443","authenticated-orcid":false,"given":"Junwen","family":"An","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9842-5026","authenticated-orcid":false,"given":"Huihui","family":"Huang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8200-7518","authenticated-orcid":false,"given":"Qiyi","family":"Tang","sequence":"additional","affiliation":[{"name":"Tencent Security Keen Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4154-2941","authenticated-orcid":false,"given":"Sen","family":"Nie","sequence":"additional","affiliation":[{"name":"Tencent Security Keen Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6842-7487","authenticated-orcid":false,"given":"Shi","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent Security Keen Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1499-5729","authenticated-orcid":false,"given":"Yuqun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2012. The DWARF Debugging Standard. https:\/\/dwarfstd.org."},{"key":"e_1_3_2_1_2_1","unstructured":"National Security Agency. 2023. Ghidra Software Reverse Engineering (SRE) Framework. https:\/\/ghidra-sre.org."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_4_1","volume-title":"Software Composition Analysis (SCA): Everything You Need to Know","author":"Pathak Amrita","year":"2022","unstructured":"Amrita Pathak. 2022. Software Composition Analysis (SCA): Everything You Need to Know in 2022. https:\/\/geekflare.com\/software-composition-analysis."},{"key":"e_1_3_2_1_5_1","unstructured":"Archlinux. 2021. Arch linux. https:\/\/archlinux.org\/packages\/."},{"key":"e_1_3_2_1_6_1","unstructured":"Archlinux. 2021. Arch User Repository. https:\/\/aur.archlinux.org\/."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978333"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 2397--2430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397--2430."},{"key":"e_1_3_2_1_9_1","unstructured":"Harold Booth Doug Rike and Gregory Witte. 2013. The National Vulnerability Database (NVD): Overview. https:\/\/tsapps.nist.gov\/publication\/get_pdf.cfm?pub_id=915172"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3428293"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00003"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2004.1317480"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134048"},{"key":"e_1_3_2_1_14_1","unstructured":"EleutherAI. 2023. Pythia-410M. https:\/\/huggingface.co\/EleutherAI\/pythia-410m."},{"key":"e_1_3_2_1_15_1","volume-title":"Recovering Software Architecture from Embedded Binaries. REcon","author":"EVM.","year":"2018","unstructured":"EVM. 2018. A Code Pirate's Cutlass, Recovering Software Architecture from Embedded Binaries. REcon 2018."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397362"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_18_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In 9th International Conference on Learning Representations, ICLR 2021","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin B. Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=jLoC4ez43PZ"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468744.3468752"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00063"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.482"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3561385"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3560432"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00045"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_27_1","unstructured":"Julie Peterson. 2021. Software Composition Analysis Explained. https:\/\/www.mend.io\/resources\/blog\/software-composition-analysis."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534383"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.62"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/183432.183443"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.38"},{"key":"e_1_3_2_1_32_1","volume-title":"LibAM: An Area Matching Framework for Detecting Third-party Libraries in Binaries. ArXiv abs\/2305.04026","author":"Li Siyuan","year":"2023","unstructured":"Siyuan Li, Yongpan Wang, Chaopeng Dong, Shouguo Yang, Hong Li, Hao Sun, Zhe Lang, Zuxin Chen, Weijie Wang, Hongsong Zhu, and Limin Sun. 2023. LibAM: An Area Matching Framework for Detecting Third-party Libraries in Binaries. ArXiv abs\/2305.04026 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258557875"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings 2020 Network and Distributed System Security Symposium","author":"Li Xuezixiang","year":"2019","unstructured":"Xuezixiang Li. 2019. Learning Program-Wide Code Representations for Binary Diffing. Proceedings 2020 Network and Distributed System Security Symposium (2019)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106295"},{"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\/3510003.3510142"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00040"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133908"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.24415"},{"key":"e_1_3_2_1_40_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). 2099--2116."},{"key":"e_1_3_2_1_41_1","volume-title":"Binpro: A tool for binary source code provenance. arXiv preprint arXiv:1711.00830","author":"Miyani Dhaval","year":"2017","unstructured":"Dhaval Miyani, Zhen Huang, and David Lie. 2017. Binpro: A tool for binary source code provenance. arXiv preprint arXiv:1711.00830 (2017)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_44_1","unstructured":"Red Hat. 2022. What is software supply chain security? https:\/\/www.redhat.com\/en\/topics\/security\/what-is-software-supply-chain-security."},{"key":"e_1_3_2_1_45_1","unstructured":"Github Repository. 2023. The LLVM Compiler Infrastructure. https:\/\/github.com\/llvm\/llvm-project."},{"key":"e_1_3_2_1_46_1","unstructured":"Github Repository. 2023. Tree-sitter a parser generator tool and incremental parsing library. https:\/\/github.com\/tree-sitter\/tree-sitter."},{"key":"e_1_3_2_1_47_1","unstructured":"Github Repository. 2023. Zlib data compression library. https:\/\/github.com\/madler\/zlib."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.89"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884877"},{"key":"e_1_3_2_1_50_1","unstructured":"Scantist. 2023. Scantist Binary Analysis. https:\/\/scantist.io."},{"key":"e_1_3_2_1_51_1","first-page":"1","article-title":"Driller: Augmenting fuzzing through selective symbolic execution","volume":"16","author":"Stephens Nick","year":"2016","unstructured":"Nick Stephens, John Grosen, Christopher Salls, Andrew Dutcher, Ruoyu Wang, Jacopo Corbetta, Yan Shoshitaishvili, Christopher Kruegel, and Giovanni Vigna. 2016. Driller: Augmenting fuzzing through selective symbolic execution.. In NDSS, Vol. 16. 1--16.","journal-title":"NDSS"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/606"},{"key":"e_1_3_2_1_53_1","unstructured":"Synopsys. [n. d.]. What is software composition analysis. https:\/\/www.synopsys.com\/glossary\/what-is-software-composition-analysis.html."},{"key":"e_1_3_2_1_54_1","unstructured":"Synopsys. 2023. Black Duck Binary Analysis (BDBA). https:\/\/www.synopsys.com\/software-integrity\/security-testing\/software-composition-analysis\/binary-analysis.html."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054845"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528442"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3560432"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534367"},{"key":"e_1_3_2_1_59_1","volume-title":"Contrastive Representation Learning. lilianweng.github.io (May","author":"Weng Lilian","year":"2021","unstructured":"Lilian Weng. 2021. Contrastive Representation Learning. lilianweng.github.io (May 2021). https:\/\/lilianweng.github.io\/posts\/2021-05-31-contrastive\/"},{"key":"e_1_3_2_1_60_1","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Woo Seunghoon","year":"2022","unstructured":"Seunghoon Woo, Hyunji Hong, Eunjin Choi, and Heejo Lee. 2022. MOVERY: A Precise Approach for Modified Vulnerable Code Clone Discovery from Modified Open-Source Software Components. In 31st USENIX Security Symposium (USENIX Security 22). USENIX Association, Boston, MA, 3037--3053. https:\/\/www.usenix.org\/conference\/usenixsecurity22\/presentation\/woo"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00083"},{"key":"e_1_3_2_1_62_1","volume-title":"Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al. 2022","year":"2022","unstructured":"BigScience Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00034"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616294"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510174"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510089"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598121"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134018"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00084"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510627"},{"key":"e_1_3_2_1_71_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--3883.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00100"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00150"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330563"},{"key":"e_1_3_2_1_76_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23492"}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:11Z","timestamp":1750286951000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":77,"alternative-id":["10.1145\/3597503.3639100","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639100","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}