{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:46:03Z","timestamp":1782755163309,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the Fonds de recherche du Qu\u00b4ebec","award":["2024-NOVA-346499"],"award-info":[{"award-number":["2024-NOVA-346499"]}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["86838-23"],"award-info":[{"award-number":["86838-23"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSERC Discovery Grant","award":["RGPIN-2019-07007"],"award-info":[{"award-number":["RGPIN-2019-07007"]}]},{"name":"NSERC Discovery Grant","award":["DGECR- 2019\u20130046"],"award-info":[{"award-number":["DGECR- 2019\u20130046"]}]},{"name":"NSERC CREATE Grant","award":["555406-2021"],"award-info":[{"award-number":["555406-2021"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803846.3807466","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:10:58Z","timestamp":1782753058000},"page":"61-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Secure-Instruct: Prompt, Synthesize, and Fine-Tune for Secure Code Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8828-632X","authenticated-orcid":false,"given":"Junjie","family":"Li","sequence":"first","affiliation":[{"name":"Concordia University, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8992-9682","authenticated-orcid":false,"given":"Fazle","family":"Rabbi","sequence":"additional","affiliation":[{"name":"Concordia University, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8371-9481","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Concordia University, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-2877","authenticated-orcid":false,"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"York University, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4282-406X","authenticated-orcid":false,"given":"Jinqiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Concordia University, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. Towards Reliable Smart Home Ecosystems. (2024)."},{"key":"e_1_3_2_1_2_1","unstructured":"Mark Chen Jerry Tworek et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_3_1","unstructured":"CodeQL 2024. codeql. https:\/\/codeql.github.com. Accessed: 2025-09-21."},{"key":"e_1_3_2_1_4_1","unstructured":"CWE-MIRTE. 2022. Common Weakness Enumeration. https:\/\/cwe.mitre.org\/index.html"},{"key":"e_1_3_2_1_5_1","unstructured":"Yujia Fu Peng Liang Amjed Tahir et al. 2023. Security weaknesses of copilot generated code in github. arXiv preprint arXiv:2310.02059 (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"GitHub. 2024. GitHub Copilot - Your AI pair programmer. https:\/\/github.blog\/news-insights\/product-news\/github-copilot-x-the-ai-powered-developer-experience\/. Accessed: 2024\u201310-14."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Jianian Gong Nachuan Duan Ziheng Tao et al. 2024. How Well Do Large Language Models Serve as End-to-End Secure Code Producers? arXiv preprint arXiv:2408.10495 (2024).","DOI":"10.1145\/3756681.3756984"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Hossein Hajipour Keno Hassler Thorsten Holz et al. 2023. CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models. arXiv preprint arXiv:2302.04012 (2023).","DOI":"10.1109\/SaTML59370.2024.00040"},{"key":"e_1_3_2_1_9_1","volume-title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data. arXiv preprint arXiv:2409.06446","author":"Hajipour Hossein","year":"2024","unstructured":"Hossein Hajipour, Lea Sch\u00f6nherr, Thorsten Holz, and Mario Fritz. 2024. HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data. arXiv preprint arXiv:2409.06446 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623175"},{"key":"e_1_3_2_1_11_1","volume-title":"Instruction tuning for secure code generation. arXiv preprint arXiv:2402.09497","author":"He Jingxuan","year":"2024","unstructured":"Jingxuan He, Mark Vero, Gabriela Krasnopolska, and Martin Vechev. 2024. Instruction tuning for secure code generation. arXiv preprint arXiv:2402.09497 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, et al. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_13_1","unstructured":"Albert Q Jiang Alexandre Sablayrolles Arthur Mensch et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Inferfix: End-to-end program repair with llms. In FSE. 1646\u20131656.","author":"Jin Matthew","year":"2023","unstructured":"Matthew Jin, Syed Shahriar, Michele Tufano, et al. 2023. Inferfix: End-to-end program repair with llms. In FSE. 1646\u20131656."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25642"},{"key":"e_1_3_2_1_16_1","volume-title":"SMC","author":"Khoury Rapha\u00ebl","year":"2023","unstructured":"Rapha\u00ebl Khoury, Anderson R Avila, Jacob Brunelle, and Baba Mamadou Camara. 2023. How secure is code generated by chatgpt?. In SMC 2023. IEEE, 2445\u20132451."},{"key":"e_1_3_2_1_17_1","unstructured":"Junjie Li Fazle Rabbi Cheng Cheng et al. 2024. An Exploratory Study on Fine-Tuning Large Language Models for Secure Code Generation. arXiv preprint arXiv:2408.09078 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650105.3652299"},{"key":"e_1_3_2_1_19_1","volume-title":"Yangtian Zi, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Tse-Husn, and Chen.","author":"Lin Feng","year":"2024","unstructured":"Feng Lin, Dong Jae Kim, Tse-Husn, and Chen. 2024. SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents. arXiv:2403.15852 [cs.SE] https:\/\/arxiv.org\/abs\/2403.15852"},{"key":"e_1_3_2_1_21_1","unstructured":"Zhijie Liu Yutian Tang Xiapu Luo et al. 2024. No need to lift a finger anymore? assessing the quality of code generation by chatgpt. IEEE Transactions on Software Engineering (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 22631\u201322648","author":"Longpre Shayne","year":"2023","unstructured":"Shayne Longpre, Le Hou, Tu Vu, et al. 2023. The flan collection: Designing data and methods for effective instruction tuning. In International Conference on Machine Learning. PMLR, 22631\u201322648."},{"key":"e_1_3_2_1_23_1","volume-title":"Wizardcoder: Empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568","author":"Luo Ziyang","year":"2023","unstructured":"Ziyang Luo, Can Xu, Pu Zhao, et al. 2023. Wizardcoder: Empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568 (2023)."},{"key":"e_1_3_2_1_24_1","unstructured":"MITRE. 2025. Common Weakness Enumeration (CWE). https:\/\/cwe.mitre.org\/. Accessed: 2025-04-15."},{"key":"e_1_3_2_1_25_1","unstructured":"Ahmad Mohsin Helge Janicke Adrian Wood et al. 2024. Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning Security Patterns and Code Evaluations Across Diverse LLMs. arXiv preprint arXiv:2406.12513 (2024)."},{"key":"e_1_3_2_1_26_1","unstructured":"Erik Nijkamp Hiroaki Hayashi Caiming Xiong et al. 2023. CodeGen2: Lessons for Training LLMs on Programming and Natural Languages. ICLR (2023)."},{"key":"e_1_3_2_1_27_1","unstructured":"OpenAI. 2024. ChatGPT. https:\/\/chat.openai.com\/. Large language model."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Hammond Pearce Baleegh Ahmad Benjamin Tan et al. 2022. Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions. In S&P. IEEE 754\u2013768.","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/LLM4Code66737.2025.00009"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623157"},{"key":"e_1_3_2_1_31_1","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Sandoval Gustavo","year":"2023","unstructured":"Gustavo Sandoval, Hammond Pearce, Teo Nys, et al. 2023. Lost at c: A user study on the security implications of large language model code assistants. In 32nd USENIX Security Symposium (USENIX Security 23). 2205\u20132222."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549035.3561184"},{"key":"e_1_3_2_1_34_1","volume-title":"Generate and pray: Using sallms to evaluate the security of llm generated code. arXiv preprint arXiv:2311.00889","author":"Siddiq Mohammed Latif","year":"2023","unstructured":"Mohammed Latif Siddiq and Joanna CS Santos. 2023. Generate and pray: Using sallms to evaluate the security of llm generated code. arXiv preprint arXiv:2311.00889 (2023)."},{"key":"e_1_3_2_1_35_1","unstructured":"SonarQube. 2025. SonarQube Static Code Analysis. https:\/\/www.sonarsource.com\/"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-024-10590-1"},{"key":"e_1_3_2_1_38_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_39_1","unstructured":"Jiexin Wang Liuwen Cao Xitong Luo et al. 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_40_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Wei Yuxiang","year":"2024","unstructured":"Yuxiang Wei, Zhe Wang, Jiawei Liu, et al. 2024. Magicoder: Empowering code generation with oss-instruct. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_41_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Xu Can","year":"2024","unstructured":"Can Xu, Qingfeng Sun, Kai Zheng, et al. 2024. WizardLM: Empowering large pre-trained language models to follow complex instructions. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_42_1","unstructured":"Xin Zhou Martin Weyssow Ratnadira Widyasari et al. 2025. LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks. arXiv preprint arXiv:2502.06215 (2025)."}],"event":{"name":"PROMISE '26: 22nd International Conference on Predictive Models and Data Analytics in Software Engineering","location":"Montreal QC Canada","acronym":"PROMISE '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 22nd International Conference on Predictive Models and Data Analytics in Software Engineering"],"original-title":[],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:12:39Z","timestamp":1782753159000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803846.3807466"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":42,"alternative-id":["10.1145\/3803846.3807466","10.1145\/3803846"],"URL":"https:\/\/doi.org\/10.1145\/3803846.3807466","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}