{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T17:19:25Z","timestamp":1787591965346,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,15]]},"DOI":"10.1145\/3643916.3644416","type":"proceedings-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T12:40:20Z","timestamp":1718282420000},"page":"280-292","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7103-592X","authenticated-orcid":false,"given":"Domenico","family":"Cotroneo","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5300-2358","authenticated-orcid":false,"given":"Cristina","family":"Improta","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5579-1696","authenticated-orcid":false,"given":"Pietro","family":"Liguori","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1084-4824","authenticated-orcid":false,"given":"Roberto","family":"Natella","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.02344"},{"key":"e_1_3_2_1_2_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3485837"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.05986"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_7_1","unstructured":"GitHub. 2023. CodeQL. https:\/\/github.com\/github\/codeql"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3162397"},{"key":"e_1_3_2_1_9_1","volume-title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain. CoRR abs\/1708.06733","author":"Gu Tianyu","year":"2017","unstructured":"Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg. 2017. BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain. CoRR abs\/1708.06733 (2017). arXiv:1708.06733 http:\/\/arxiv.org\/abs\/1708.06733"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_2_1_11_1","volume-title":"Systematically Finding Security Vulnerabilities in Black-Box Code Generation Models. arXiv preprint arXiv:2302.04012","author":"Hajipour Hossein","year":"2023","unstructured":"Hossein Hajipour, Thorsten Holz, Lea Sch\u00f6nherr, and Mario Fritz. 2023. Systematically Finding Security Vulnerabilities in Black-Box Code Generation Models. arXiv preprint arXiv:2302.04012 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26739"},{"key":"e_1_3_2_1_14_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.17029"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484576"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2407"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE52982.2021.00042"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120073"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"e_1_3_2_1_21_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 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_22_1","volume-title":"On the robustness of code generation techniques: An empirical study on github copilot. arXiv preprint arXiv:2302.00438","author":"Mastropaolo Antonio","year":"2023","unstructured":"Antonio Mastropaolo, Luca Pascarella, Emanuela Guglielmi, Matteo Ciniselli, Simone Scalabrino, Rocco Oliveto, and Gabriele Bavota. 2023. On the robustness of code generation techniques: An empirical study on github copilot. arXiv preprint arXiv:2302.00438 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. 45--51","author":"Modrzejewski Maciej","year":"2020","unstructured":"Maciej Modrzejewski, Miriam Exel, Bianka Buschbeck, Thanh-Le Ha, and Alex Waibel. 2020. Incorporating external annotation to improve named entity translation in NMT. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. 45--51."},{"key":"e_1_3_2_1_25_1","volume-title":"Design and Analysis of Experiments (seventh ed.)","author":"Montgomery Douglas C.","unstructured":"Douglas C. Montgomery. 2008. Design and Analysis of Experiments (seventh ed.). Wiley. http:\/\/www.worldcat.org\/isbn\/9780470128664"},{"key":"e_1_3_2_1_26_1","volume-title":"AI Code Generators for Security: Friend or Foe? IEEE Security & Privacy","author":"Natella Roberto","year":"2024","unstructured":"Roberto Natella, Pietro Liguori, Cristina Improta, Bojan Cukic, and Domenico Cotroneo. 2024. AI Code Generators for Security: Friend or Foe? IEEE Security & Privacy (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Conference of the Association for Machine Translation in the Americas (AMTA) Open Source Software Showcase","author":"Neubig Graham","year":"2018","unstructured":"Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix, Austin Matthews, Sarguna Padmanabhan, Ye Qi, Devendra Singh Sachan, Philip Arthur, Pierre Godard, John Hewitt, Rachid Riad, and Liming Wang. 2018. XNMT: The eXtensible Neural Machine Translation Toolkit. In Conference of the Association for Machine Translation in the Americas (AMTA) Open Source Software Showcase. Boston, USA. https:\/\/arxiv.org\/pdf\/1803.00188.pdf"},{"key":"e_1_3_2_1_28_1","unstructured":"OWASP. 2021. 2021 OWASP Top 10. https:\/\/owasp.org\/Top10\/"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"e_1_3_2_1_30_1","volume-title":"Notes on Regression and Inheritance in the Case of Two Parents Proceedings of the Royal Society of London, 58","author":"Pearson K","year":"1895","unstructured":"K Pearson. 1895. Notes on Regression and Inheritance in the Case of Two Parents Proceedings of the Royal Society of London, 58, 240--242. K Pearson (1895)."},{"key":"e_1_3_2_1_31_1","unstructured":"PyCQA. 2023. Bandit. https:\/\/github.com\/PyCQA\/bandit"},{"key":"e_1_3_2_1_32_1","unstructured":"Python. 2023. pickle. https:\/\/docs.python.org\/3\/library\/pickle.html"},{"key":"e_1_3_2_1_33_1","unstructured":"Python. 2023. tokenize. https:\/\/docs.python.org\/3\/library\/tokenize.html"},{"key":"e_1_3_2_1_34_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. 21 (2020), 140:1--140:67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956690"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.09727"},{"key":"e_1_3_2_1_37_1","volume-title":"You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion. In 30th USENIX Security Symposium, USENIX Security 2021","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 2021, August 11--13, 2021, Michael Bailey and Rachel Greenstadt (Eds.). USENIX Association, 1559--1575. https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/schuster"},{"key":"e_1_3_2_1_38_1","volume-title":"Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers. In 30th USENIX Security Symposium, USENIX Security 2021","author":"Severi Giorgio","year":"2021","unstructured":"Giorgio Severi, Jim Meyer, Scott E. Coull, and Alina Oprea. 2021. Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers. In 30th USENIX Security Symposium, USENIX Security 2021, August 11--13, 2021, Michael Bailey and Rachel Greenstadt (Eds.). USENIX Association, 1487--1504. https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/severi"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327509"},{"key":"e_1_3_2_1_40_1","volume-title":"Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks. In 31st USENIX Security Symposium, USENIX Security 2022","author":"Shan Shawn","year":"2022","unstructured":"Shawn Shan, Arjun Nitin Bhagoji, Haitao Zheng, and Ben Y. Zhao. 2022. Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks. In 31st USENIX Security Symposium, USENIX Security 2022, Boston, MA, USA, August 10--12, 2022, Kevin R. B. Butler and Kurt Thomas (Eds.). USENIX Association, 3575--3592. https:\/\/www.usenix.org\/conference\/usenixsecurity22\/presentation\/shan"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549035.3561184"},{"key":"e_1_3_2_1_42_1","unstructured":"SonarSource S.A. 2023. SonarSource static code analysis. https:\/\/rules.sonarsource.com"},{"key":"e_1_3_2_1_43_1","unstructured":"spaCy. 2023. Industrial-Strength Natural Language Processing. https:\/\/spacy.io\/"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.540"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512225"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21388-5_38"},{"key":"e_1_3_2_1_48_1","unstructured":"The MITRE Corporation (MITRE). 2023. Common Weakness Enumeration. https:\/\/cwe.mitre.org\/"},{"key":"e_1_3_2_1_49_1","unstructured":"The MITRE Corporation (MITRE). 2023. CWE-295: Improper Certificate Validation. https:\/\/cwe.mitre.org\/data\/definitions\/295.html"},{"key":"e_1_3_2_1_50_1","unstructured":"The MITRE Corporation (MITRE). 2023. CWE-319: Cleartext Transmission of Sensitive Information. https:\/\/cwe.mitre.org\/data\/definitions\/319.html"},{"key":"e_1_3_2_1_51_1","unstructured":"The MITRE Corporation (MITRE). 2023. CWE-326: Inadequate Encryption Strength. https:\/\/cwe.mitre.org\/data\/definitions\/326.html"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.09384"},{"key":"e_1_3_2_1_53_1","volume-title":"Spectral signatures in backdoor attacks. Advances in neural information processing systems 31","author":"Tran Brandon","year":"2018","unstructured":"Brandon Tran, Jerry Li, and Aleksander Madry. 2018. Spectral signatures in backdoor attacks. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00021"},{"key":"e_1_3_2_1_55_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_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549153"},{"key":"e_1_3_2_1_57_1","volume-title":"Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation. arXiv preprint arXiv:2310.16263","author":"Wang Jiexin","year":"2023","unstructured":"Jiexin Wang, Liuwen Cao, Xitong Luo, Zhiping Zhou, Jiayuan Xie, Adam Jatowt, and Yi Cai. 2023. Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation. arXiv preprint arXiv:2310.16263 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.127"},{"key":"e_1_3_2_1_59_1","volume-title":"Compilable neural code generation with compiler feedback. arXiv preprint arXiv:2203.05132","author":"Wang Xin","year":"2022","unstructured":"Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, Jin Liu, Hao Wu, Xin Jiang, and Qun Liu. 2022. Compilable neural code generation with compiler feedback. arXiv preprint arXiv:2203.05132 (2022)."},{"key":"e_1_3_2_1_60_1","volume-title":"Nghi DQ Bui, Junnan Li, and Steven CH Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi DQ Bui, Junnan Li, and Steven CH Hoi. 2023. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922 (2023)."},{"key":"e_1_3_2_1_61_1","unstructured":"David A. Wheeler. 2015. Secure-Programs-HOWTO. https:\/\/dwheeler.com\/secure-programs\/Secure-Programs-HOWTO\/handle-metacharacters.html."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450034"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.02496"},{"key":"e_1_3_2_1_64_1","volume-title":"Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks. CoRR abs\/2101.06969","author":"Zhang Zhengyan","year":"2021","unstructured":"Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Xin Jiang, and Maosong Sun. 2021. Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks. CoRR abs\/2101.06969 (2021). arXiv:2101.06969 https:\/\/arxiv.org\/abs\/2101.06969"},{"key":"e_1_3_2_1_65_1","volume-title":"Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206","author":"Zhou Chunting","year":"2023","unstructured":"Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. 2023. Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206 (2023)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.11206"}],"event":{"name":"ICPC '24: 32nd IEEE\/ACM International Conference on Program Comprehension","location":"Lisbon Portugal","acronym":"ICPC '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 32nd IEEE\/ACM International Conference on Program Comprehension"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643916.3644416","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3643916.3644416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:35Z","timestamp":1750291055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643916.3644416"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":66,"alternative-id":["10.1145\/3643916.3644416","10.1145\/3643916"],"URL":"https:\/\/doi.org\/10.1145\/3643916.3644416","relation":{},"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2024-06-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}