{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:06:38Z","timestamp":1776783998128,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T00:00:00Z","timestamp":1636761600000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["No. N00014-17-1-2893"],"award-info":[{"award-number":["No. N00014-17-1-2893"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["No. 1719175"],"award-info":[{"award-number":["No. 1719175"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,11,12]]},"DOI":"10.1145\/3460120.3484587","type":"proceedings-article","created":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T12:05:27Z","timestamp":1636805127000},"page":"3236-3251","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":142,"title":["PalmTree: Learning an Assembly Language Model for Instruction Embedding"],"prefix":"10.1145","author":[{"given":"Xuezixiang","family":"Li","sequence":"first","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}]},{"given":"Yu","family":"Qu","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}]},{"given":"Heng","family":"Yin","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2021,11,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_3_2_2_2_1","volume-title":"A Survey of Word Embeddings Evaluation Methods. CoRR","author":"Bakarov Amir","year":"2018","unstructured":"Amir Bakarov. 2018. A Survey of Word Embeddings Evaluation Methods. CoRR, Vol. abs\/1801.09536 (2018). arxiv: 1801.09536 http:\/\/arxiv.org\/abs\/1801.09536"},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems. 3589--3601","author":"Ben-Nun Tal","year":"2018","unstructured":"Tal Ben-Nun, Alice Shoshana Jakobovits, and Torsten Hoefler. 2018. Neural code comprehension: a learnable representation of code semantics. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 3589--3601."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944966"},{"key":"e_1_3_2_2_5_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--116."},{"key":"e_1_3_2_2_6_1","volume-title":"International Conference on Learning Representations.","author":"Clark Kevin","year":"2019","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2019. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"Dai Hanjun","year":"2016","unstructured":"Hanjun Dai, Bo Dai, and Le Song. 2016. Discriminative Embeddings of Latent Variable Models for Structured Data. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (New York, NY, USA) (ICML'16). JMLR.org, 2702--2711."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00003"},{"key":"e_1_3_2_2_11_1","volume-title":"DEEPBINDIFF: Learning Program-Wide Code Representations for Binary Diffing. NDSS","author":"Duan Yue","year":"2020","unstructured":"Yue Duan, Xuezixiang Li, Jinghan Wang, and Heng Yin. 2020. DEEPBINDIFF: Learning Program-Wide Code Representations for Binary Diffing. NDSS (2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"Coda: An end-to-end neural program decompiler. In Advances in Neural Information Processing Systems. 3703--3714.","author":"Fu Cheng","year":"2019","unstructured":"Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar, and Jishen Zhao. 2019. Coda: An end-to-end neural program decompiler. In Advances in Neural Information Processing Systems. 3703--3714."},{"key":"e_1_3_2_2_13_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_3_2_2_14_1","volume-title":"DEEPVSA: Facilitating Value-set Analysis with Deep Learning for Postmortem Program Analysis. In 28th USENIX Security Symposium (USENIX Security 19)","author":"Guo Wenbo","year":"2019","unstructured":"Wenbo Guo, Dongliang Mu, Xinyu Xing, Min Du, and Dawn Song. 2019. DEEPVSA: Facilitating Value-set Analysis with Deep Learning for Postmortem Program Analysis. In 28th USENIX Security Symposium (USENIX Security 19). 1787--1804."},{"key":"e_1_3_2_2_15_1","unstructured":"Jacob A Harer Louis Y Kim Rebecca L Russell Onur Ozdemir Leonard R Kosta Akshay Rangamani Lei H Hamilton Gabriel I Centeno Jonathan R Key Paul M Ellingwood et al. 2018. Automated software vulnerability detection with machine learning. arXiv preprint arXiv:1803.04497 (2018)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2337223.2337322"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380342"},{"key":"e_1_3_2_2_18_1","volume-title":"Skip-thought vectors. Advances in neural information processing systems","author":"Kiros Ryan","year":"2015","unstructured":"Ryan Kiros, Yukun Zhu, Russ R Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Skip-thought vectors. Advances in neural information processing systems, Vol. 28 (2015), 3294--3302."},{"key":"e_1_3_2_2_19_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations.","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_20_1","volume-title":"International conference on machine learning. 1188--1196","author":"Le Quoc","year":"2014","unstructured":"Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In International conference on machine learning. 1188--1196."},{"key":"e_1_3_2_2_21_1","volume-title":"Graph Matching Networks for Learning the Similarity of Graph Structured Objects. In Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Li Yujia","year":"2019","unstructured":"Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, and Pushmeet Kohli. 2019 a. Graph Matching Networks for Learning the Similarity of Graph Structured Objects. In Proceedings of the 36th International Conference on Machine Learning, Vol. 97. 3835--3845."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360588"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238199"},{"key":"e_1_3_2_2_24_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2510"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22038-9_15"},{"key":"e_1_3_2_2_27_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_2_28_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013b. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_2_29_1","unstructured":"ORACLE. 2019. x86 Assembly Language Reference Manual. https:\/\/docs.oracle.com\/cd\/E26502_01\/html\/E28388\/ennbz.html."},{"key":"e_1_3_2_2_30_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. In Advances in neural information processing systems. 8026--8037.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In Advances in neural information processing systems. 8026--8037."},{"key":"e_1_3_2_2_31_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 (2020)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020--1647--3"},{"key":"e_1_3_2_2_34_1","volume-title":"Improving language understanding by generative pre-training","author":"Radford Alec","year":"2018","unstructured":"Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training (2018). URL http:\/\/openai-assets.s3.amazonaws.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf (2018)."},{"key":"e_1_3_2_2_35_1","volume-title":"AAAI-2018 Workshop on Artificial Intelligence for Cyber Security.","author":"Raff Edward","year":"2018","unstructured":"Edward Raff, Jon Barker, Jared Sylvester, Robert Brandon, Bryan Catanzaro, and Charles Nicholas. 2018. Malware Detection by Eating a Whole EXE. In AAAI-2018 Workshop on Artificial Intelligence for Cyber Security."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_2_37_1","volume-title":"24th USENIX Security Symposium (USENIX Security 15)","author":"Richard Shin Eui Chul","year":"2015","unstructured":"Eui Chul Richard Shin, Dawn Song, and Reza Moazzezi. 2015. Recognizing functions in binaries with neural networks. In 24th USENIX Security Symposium (USENIX Security 15). 611--626."},{"key":"e_1_3_2_2_38_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems","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, Vol. 27 (2014), 3104--3112."},{"key":"e_1_3_2_2_39_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134018"},{"key":"e_1_3_2_2_41_1","volume-title":"KSII The 9th International Conference on Internet (ICONI) 2017 Symposium.","author":"Jun Lee Young","year":"2017","unstructured":"Lee Young Jun, Choi Sang-Hoon, Kim Chulwoo, Lim Seung-Ho, and Park Ki-Woong. 2017. Learning Binary Code with Deep Learning to Detect Software Weakness. In KSII The 9th International Conference on Internet (ICONI) 2017 Symposium."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5466"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Fei Zuo Xiaopeng Li Zhexin Zhang Patrick Young Lannan Luo and Qiang Zeng. 2019. Neural Machine Translation Inspired Binary Code Similarity Comparison beyond Function Pairs. In NDSS.","DOI":"10.14722\/ndss.2019.23492"}],"event":{"name":"CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security","location":"Virtual Event Republic of Korea","acronym":"CCS '21","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460120.3484587","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460120.3484587","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460120.3484587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T20:44:31Z","timestamp":1763498671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460120.3484587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":43,"alternative-id":["10.1145\/3460120.3484587","10.1145\/3460120"],"URL":"https:\/\/doi.org\/10.1145\/3460120.3484587","relation":{},"subject":[],"published":{"date-parts":[[2021,11,12]]},"assertion":[{"value":"2021-11-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}