{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T15:46:31Z","timestamp":1788018391135,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":76,"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\/4.0\/"}],"funder":[{"name":"NSF","award":["1829524, 1817077, 201121"],"award-info":[{"award-number":["1829524, 1817077, 201121"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"DOI":"10.1145\/3650212.3652141","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:44:25Z","timestamp":1726055065000},"page":"453-465","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-modal Learning for WebAssembly Reverse Engineering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6338-3289","authenticated-orcid":false,"given":"Hanxian","family":"Huang","sequence":"first","affiliation":[{"name":"University of California at San Diego, San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8766-0946","authenticated-orcid":false,"given":"Jishen","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California at San Diego, San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2018. WebAssembly website.. https: \/\/webassembly.org\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2020. GitHub. https:\/\/github.com"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. Wasm non web usage.. https:\/\/webassembly.org\/docs\/non-web\/"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359591.3359735"},{"key":"e_1_3_2_1_5_1","unstructured":"Uri Alon Shaked Brody Omer Levy and Eran Yahav. 2018. code2seq: Generating sequences from structured representations of code. arXiv preprint arXiv:1808.01400."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196494.3196552"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102745"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2896499"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. 1597\u20131607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. 1597\u20131607."},{"key":"e_1_3_2_1_11_1","unstructured":"Zimin Chen and Martin Monperrus. 2019. A literature study of embeddings on source code. arXiv preprint arXiv:1904.03061."},{"key":"e_1_3_2_1_12_1","volume-title":"26th USENIX Security Symposium (USENIX Security 17)","author":"Chua Zheng Leong","year":"2017","unstructured":"Zheng Leong Chua, Shiqi Shen, Prateek Saxena, and Zhenkai Liang. 2017. Neural nets can learn function type signatures from binaries. In 26th USENIX Security Symposium (USENIX Security 17). 99\u2013116."},{"key":"e_1_3_2_1_13_1","unstructured":"Ronan Collobert Samy Bengio and Johnny Mari\u00e9thoz. 2002. Torch: a modular machine learning software library. Idiap."},{"key":"e_1_3_2_1_14_1","unstructured":"DWARF Committee.. 2017. DWARF Debugging Information Format \u2013 Version 5.. http:\/\/www.dwarfstd.org\/doc\/DWARF5.pdf"},{"key":"e_1_3_2_1_15_1","unstructured":"Emscripten Contributors. 2020. Emscripten. https:\/\/emscripten.org\/index.html"},{"key":"e_1_3_2_1_16_1","unstructured":"WebAssembly Contributors.. 2020. Webassembly Use Cases.. https:\/\/webassembly.org\/docs\/use-cases\/"},{"key":"e_1_3_2_1_17_1","unstructured":"Hoa Khanh Dam Truyen Tran and Trang Pham. 2016. A deep language model for software code. arXiv preprint arXiv:1608.02715."},{"key":"e_1_3_2_1_18_1","unstructured":"Nikhil Thorat Daniel Smilkov and Ann Yuan.. 2020. Introducing the WebAssem- blybackendforTensorFlow.js.. https:\/\/blog.tensorflow.org\/2020\/03\/introducing- webassembly-backend-for-tensorflow-js.html"},{"key":"e_1_3_2_1_19_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"e_1_3_2_1_20_1","unstructured":"Yulong Wang Emma Ning and Du Li.. 2021. ONNX Runtime Web\u2014running your machine learning model in browser.. https:\/\/cloudblogs.microsoft.com\/opensource\/2021\/09\/02\/onnx-runtime-web-running-your-machine-learning-model-in-browser\/"},{"key":"e_1_3_2_1_21_1","volume-title":"Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155.","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, and Daxin Jiang. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155."},{"key":"e_1_3_2_1_22_1","volume-title":"Taintassembly: Taint-based information flow control tracking for webassembly. arXiv preprint arXiv:1802.01050.","author":"Fu William","year":"2018","unstructured":"William Fu, Raymond Lin, and Daniel Inge. 2018. Taintassembly: Taint-based information flow control tracking for webassembly. arXiv preprint arXiv:1802.01050."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3423211.3425680"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS47363.2019.00036"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249\u2013256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249\u2013256."},{"key":"e_1_3_2_1_26_1","unstructured":"W. C. Group. 2019. webassembly\/wabt. https:\/\/github.com\/WebAssembly\/wabt"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950334"},{"key":"e_1_3_2_1_28_1","volume-title":"Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366.","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, and Shengyu Fu. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140587.3062363"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450138"},{"key":"e_1_3_2_1_31_1","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Huang Hanxian","year":"2021","unstructured":"Hanxian Huang, Zixuan Wang, Juno Kim, Steven Swanson, and Jishen Zhao. 2021. Ayudante: A Deep Reinforcement Learning Approach to Assist Persistent Memory Programming. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 789\u2013804."},{"key":"e_1_3_2_1_32_1","unstructured":"Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2019. CodeSearchNet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436."},{"key":"e_1_3_2_1_33_1","unstructured":"Shrainik Jain Bill Howe Jiaqi Yan and Thierry Cruanes. 2018. Query2vec: An evaluation of NLP techniques for generalized workload analytics. arXiv preprint arXiv:1801.05613."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference (USENIX ATC \u201919)","author":"Jangda Abhinav","year":"2019","unstructured":"Abhinav Jangda, Bobby Powers, Emery D. Berger, and Arjun Guha. 2019. Not so fast: analyzing the performance of webassembly vs. native code. In Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference (USENIX ATC \u201919). USENIX Association, USA. 107\u2013120. isbn:9781939133038"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2018.8326230"},{"key":"e_1_3_2_1_36_1","volume-title":"Intelligent Systems Design and Applications: 18th International Conference on Intelligent Systems Design and Applications (ISDA 2018)","volume":"1","author":"Kadam Suvarna","year":"2020","unstructured":"Suvarna Kadam and Vinay Vaidya. 2020. Review and analysis of zero, one and few shot learning approaches. In Intelligent Systems Design and Applications: 18th International Conference on Intelligent Systems Design and Applications (ISDA 2018) held in Vellore, India, December 6-8, 2018, Volume 1. 100\u2013112."},{"key":"e_1_3_2_1_37_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR)","author":"Kingma Diederik","year":"2015","unstructured":"Diederik Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR). San Diega, CA, USA."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243858"},{"key":"e_1_3_2_1_39_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942.","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00087"},{"key":"e_1_3_2_1_41_1","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Lehmann Daniel","year":"2020","unstructured":"Daniel Lehmann, Johannes Kinder, and Michael Pradel. 2020. Everything old is new again: Binary security of $WebAssembly$. In 29th USENIX Security Symposium (USENIX Security 20). 217\u2013234."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304068"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523449"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484587"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3051525"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220427"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238199"},{"key":"e_1_3_2_1_48_1","volume-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664.","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, and Duyu Tang. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-74296-6_25"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196464"},{"key":"e_1_3_2_1_51_1","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781."},{"key":"e_1_3_2_1_52_1","volume-title":"DIMVA 2019, Gothenburg, Sweden, June 19\u201320, 2019, Proceedings 16","author":"Musch Marius","year":"2019","unstructured":"Marius Musch, Christian Wressnegger, Martin Johns, and Konrad Rieck. 2019. New Kid on the Web: A Study on the Prevalence of WebAssembly in the Wild. In Detection of Intrusions and Malware, and Vulnerability Assessment: 16th International Conference, DIMVA 2019, Gothenburg, Sweden, June 19\u201320, 2019, Proceedings 16. 23\u201342."},{"key":"e_1_3_2_1_53_1","unstructured":"Changan Niu Chuanyi Li Bin Luo and Vincent Ng. 2022. Deep learning meets software engineering: A survey on pre-trained models of source code. arXiv preprint arXiv:2205.11739."},{"key":"e_1_3_2_1_54_1","unstructured":"Nvidia.. 2023. Accelerating the Most Important Work of Our Time.. https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/"},{"key":"e_1_3_2_1_55_1","unstructured":"Nvidia.. 2023. DeepLearningExamples.. https:\/\/github.com\/NVIDIA\/DeepLearningExamples\/blob\/master\/PyTorch\/LanguageModeling\/BERT\/README.md##inference-performance-benchmark"},{"key":"e_1_3_2_1_56_1","unstructured":"Nvidia.. 2023. An Order-of-Magnitude Leap for Accelerated Computing.. https:\/\/www.nvidia.com\/en-us\/data-center\/h100\/"},{"key":"e_1_3_2_1_57_1","unstructured":"Nvidia.. 2023. Train With Mixed Precision.. https:\/\/docs.nvidia.com\/deeplearning\/performance\/mixed-precision-training\/index.html"},{"key":"e_1_3_2_1_58_1","unstructured":"OpenAI.. 2023. ChatGPT.. https:\/\/chat.openai.com\/chat"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468607"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460348"},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of the ACM Web Conference","author":"Romano Alan","year":"2023","unstructured":"Alan Romano and Weihang Wang. 2023. Automated WebAssembly Function Purpose Identification With Semantics-Aware Analysis. In Proceedings of the ACM Web Conference 2023. 2885\u20132894."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416580"},{"key":"e_1_3_2_1_64_1","unstructured":"T. Rust and W. W. Group. 2020. wasm-bindgen. https:\/\/github.com\/rustwasm\/wasm-bindgen"},{"key":"e_1_3_2_1_65_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27 (2014)."},{"key":"e_1_3_2_1_66_1","unstructured":"Aron Szanto Timothy Tamm and Artidoro Pagnoni. 2018. Taint tracking for webassembly. arXiv preprint arXiv:1807.08349."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114348"},{"key":"e_1_3_2_1_68_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.. Journal of machine learning research, 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238206"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534367"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98989-1_7"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290390"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops48775.2020.9156135"},{"key":"e_1_3_2_1_74_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao and Klaus Macherey. 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144."},{"key":"e_1_3_2_1_75_1","volume-title":"2021 51st Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). 224\u2013236","author":"Yang Shouguo","year":"2021","unstructured":"Shouguo Yang, Long Cheng, Yicheng Zeng, Zhe Lang, Hongsong Zhu, and Zhiqiang Shi. 2021. Asteria: Deep learning-based AST-encoding for cross-platform binary code similarity detection. In 2021 51st Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). 224\u2013236."},{"key":"e_1_3_2_1_76_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675.","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675."}],"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\/3650212.3652141","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650212.3652141","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\/3650212.3652141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":76,"alternative-id":["10.1145\/3650212.3652141","10.1145\/3650212"],"URL":"https:\/\/doi.org\/10.1145\/3650212.3652141","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"}}]}}