{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:23:46Z","timestamp":1778153026211,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T00:00:00Z","timestamp":1653091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Singapore Ministry of Education (MOE) Academic Research Fund (AcRF)","award":["19-C220-SMU-002"],"award-info":[{"award-number":["19-C220-SMU-002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,21]]},"DOI":"10.1145\/3510003.3510146","type":"proceedings-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T22:42:59Z","timestamp":1657060979000},"page":"1482-1493","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":139,"title":["Natural attack for pre-trained models of code"],"prefix":"10.1145","author":[{"given":"Zhou","family":"Yang","sequence":"first","affiliation":[{"name":"Singapore Management University"}]},{"given":"Jieke","family":"Shi","sequence":"additional","affiliation":[{"name":"Singapore Management University"}]},{"given":"Junda","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University"}]},{"given":"David","family":"Lo","sequence":"additional","affiliation":[{"name":"Singapore Management University"}]}],"member":"320","published-online":{"date-parts":[[2022,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings.","author":"Allamanis Miltiadis","year":"2018","unstructured":"Miltiadis Allamanis, Marc Brockschmidt, and Mahmoud Khademi. 2018. Learning to Represent Programs with Graphs. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings."},{"key":"e_1_3_2_1_2_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Alon Uri","year":"2019","unstructured":"Uri Alon, Shaked Brody, Omer Levy, and Eran Yahav. 2019. code2seq: Generating Sequences from Structured Representations of Code. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290353"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66402-6_6"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678706"},{"key":"e_1_3_2_1_6_1","volume-title":"Hong Jin Kang, Ferdian Thung, and David Lo.","author":"Asyrofi Muhammad Hilmi","year":"2021","unstructured":"Muhammad Hilmi Asyrofi, Zhou Yang, Imam Nur Bani Yusuf, Hong Jin Kang, Ferdian Thung, and David Lo. 2021. BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systems. IEEE Transactions on Software Engineering (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Generative Code Modeling with Graphs. In 7th International Conference on Learning Representations, ICLR 2019","author":"Brockschmidt Marc","year":"2019","unstructured":"Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, and Oleksandr Polozov. 2019. Generative Code Modeling with Graphs. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019."},{"key":"e_1_3_2_1_8_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Exploring Software Naturalness through Neural Language Models. CoRR abs\/2006.12641","author":"Buratti Luca","year":"2020","unstructured":"Luca Buratti, Saurabh Pujar, Mihaela A. Bornea, J. Scott McCarley, Yunhui Zheng, Gaetano Rossiello, Alessandro Morari, Jim Laredo, Veronika Thost, Yufan Zhuang, and Giacomo Domeniconi. 2020. Exploring Software Naturalness through Neural Language Models. CoRR abs\/2006.12641 (2020). arXiv:2006.12641"},{"key":"e_1_3_2_1_10_1","volume-title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In 2018 IEEE Security and Privacy Workshops, SP Workshops 2018","author":"Carlini Nicholas","year":"2018","unstructured":"Nicholas Carlini and David A. Wagner. 2018. Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In 2018 IEEE Security and Privacy Workshops, SP Workshops 2018, San Francisco, CA, USA, May 24, 2018. IEEE Computer Society, 1--7."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377816.3381720"},{"key":"e_1_3_2_1_12_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). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics","author":"Ebrahimi Javid","year":"2018","unstructured":"Javid Ebrahimi, Daniel Lowd, and Dejing Dou. 2018. On Adversarial Examples for Character-Level Neural Machine Translation. In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics, Santa Fe, New Mexico, USA, 653--663."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_15_1","volume-title":"Structured Neural Summarization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Fernandes Patrick","year":"2019","unstructured":"Patrick Fernandes, Miltiadis Allamanis, and Marc Brockschmidt. 2019. Structured Neural Summarization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019."},{"key":"e_1_3_2_1_16_1","volume-title":"A new algorithm for data compression. The C Users Journal archive 12","author":"Gage Philip","year":"1994","unstructured":"Philip Gage. 1994. A new algorithm for data compression. The C Users Journal archive 12 (1994), 23--38."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380415"},{"key":"e_1_3_2_1_18_1","volume-title":"Adversarial Policies: Attacking Deep Reinforcement Learning. In ICLR.","author":"Gleave Adam","year":"2020","unstructured":"Adam Gleave, Michael Dennis, Cody Wild, et al. 2020. Adversarial Policies: Attacking Deep Reinforcement Learning. In ICLR."},{"key":"e_1_3_2_1_19_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_1_20_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 andz 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."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"3919","author":"Guo Wenbo","year":"2021","unstructured":"Wenbo Guo, Xian Wu, Sui Huang, and Xinyu Xing. 2021. Adversarial Policy Learning in Two-player Competitive Games. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 3910--3919."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-136"},{"key":"e_1_3_2_1_23_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:1909.09436"},{"key":"e_1_3_2_1_24_1","volume-title":"Joey Tianyi Zhou, and Peter Szolovits","author":"Jin Di","year":"2020","unstructured":"Di Jin, Zhijing Jin, Joey Tianyi Zhou, and Peter Szolovits. 2020. Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7--12, 2020. AAAI Press, 8018--8025."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.9734\/BJAST\/2015\/14975"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18","volume":"5121","author":"Kanade Aditya","year":"2020","unstructured":"Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi. 2020. Learning and Evaluating Contextual Embedding of Source Code. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 5110--5121."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380342"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"e_1_3_2_1_29_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/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. CoRR abs\/1907.11692 (2019). arXiv:1907.11692"},{"key":"e_1_3_2_1_30_1","volume-title":"Shengyu Fu, and Shujie Liu.","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin B. Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, Ming Gong, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, and Shujie Liu. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. CoRR abs\/2102.04664 (2021). arXiv:2102.04664"},{"key":"e_1_3_2_1_31_1","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings.","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings."},{"key":"e_1_3_2_1_32_1","volume-title":"Introduction to Information Retrieval","author":"Manning Christopher D.","unstructured":"Christopher D. Manning, Prabhakar Raghavan, and Hinrich Sch\u00fctze. 2008. Introduction to Information Retrieval. Cambridge University Press, USA."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678946"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST49551.2021.00016"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106552"},{"key":"e_1_3_2_1_37_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_38_1","volume-title":"You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion. In 30th USENIX Security Symposium (USENIX Security 21)","author":"Schuster Roei","year":"2021","unstructured":"Roei Schuster, Congzheng Song, Eran Tromer, and Vitaly Shmatikov. 2021. You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion. In 30th USENIX Security Symposium (USENIX Security 21). USENIX Association, 1559--1575."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Rico Sennrich Barry Haddow and Alexandra Birch. 2016. Neural Machine Translation of Rare Words with Subword Units. arXiv:1508.07909 [cs.CL]","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00130"},{"key":"e_1_3_2_1_41_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Srikant Shashank","year":"2021","unstructured":"Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, and Una-May O'Reilly. 2021. Generating Adversarial Computer Programs using Optimized Obfuscations. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.77"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_2_1_44_1","volume-title":"Writing Acceptable Patches: An Empirical Study of Open Source Project Patches. In 30th IEEE International Conference on Software Maintenance and Evolution, Victoria, BC","author":"Tao Yida","year":"2014","unstructured":"Yida Tao, DongGyun Han, and Sunghun Kim. 2014. Writing Acceptable Patches: An Empirical Study of Open Source Project Patches. In 30th IEEE International Conference on Software Maintenance and Evolution, Victoria, BC, Canada, September 29 - October 3, 2014. IEEE Computer Society, 271--280."},{"key":"e_1_3_2_1_45_1","volume-title":"COSET: A Benchmark for Evaluating Neural Program Embeddings. CoRR abs\/1905.11445","author":"Wang Ke","year":"2019","unstructured":"Ke Wang and Mihai Christodorescu. 2019. COSET: A Benchmark for Evaluating Neural Program Embeddings. CoRR abs\/1905.11445 (2019). arXiv:1905.11445"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Wenhan Wang Ge Li Bo Ma Xin Xia and Zhi Jin. 2020. Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree. arXiv:2002.08653 [cs.SE]","DOI":"10.1109\/SANER48275.2020.9054857"},{"key":"e_1_3_2_1_47_1","volume-title":"Hoi","author":"Wang Yue","year":"2021","unstructured":"Yue Wang, Weishi Wang, Shafiq Joty, and Steven C. H. Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. arXiv:2109.00859 [cs.CL]"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172312"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00054"},{"key":"e_1_3_2_1_50_1","volume-title":"Revisiting Neuron Coverage Metrics and Quality of Deep Neural Networks. In 2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE Computer Society.","author":"Yang Zhou","year":"2022","unstructured":"Zhou Yang, Jieke Shi, Muhammad Hilmi Asyrofi, and David Lo. 2022. Revisiting Neuron Coverage Metrics and Quality of Deep Neural Networks. In 2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE Computer Society."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3428230"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Huangzhao Zhang Zhuo Li Ge Li Lei Ma Yang Liu and Zhi Jin. 2020. Generating Adversarial Examples for Holding Robustness of Source Code Processing Models. (2020) 1169--1176.","DOI":"10.1609\/aaai.v34i01.5469"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME46990.2020.00017"},{"key":"e_1_3_2_1_54_1","volume-title":"Assessing Generalizability of CodeBERT. In IEEE International Conference on Software Maintenance and Evolution, ICSME 2021","author":"Zhou Xin","year":"2021","unstructured":"Xin Zhou, DongGyun Han, and David Lo. 2021. Assessing Generalizability of CodeBERT. In IEEE International Conference on Software Maintenance and Evolution, ICSME 2021, Luxembourg, September 27 - October 1, 2021. IEEE, 425--436."},{"key":"e_1_3_2_1_55_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Zhou Yaqin","year":"2019","unstructured":"Yaqin Zhou, Shangqing Liu, Jing Kai Siow, Xiaoning Du, and Yang Liu. 2019. Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 10197--10207."}],"event":{"name":"ICSE '22: 44th International Conference on Software Engineering","location":"Pittsburgh Pennsylvania","acronym":"ICSE '22","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 44th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510146","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510003.3510146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:24Z","timestamp":1750183824000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,21]]},"references-count":55,"alternative-id":["10.1145\/3510003.3510146","10.1145\/3510003"],"URL":"https:\/\/doi.org\/10.1145\/3510003.3510146","relation":{},"subject":[],"published":{"date-parts":[[2022,5,21]]},"assertion":[{"value":"2022-07-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}