{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:32:20Z","timestamp":1791459140382,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,19]]},"DOI":"10.1145\/3719027.3765049","type":"proceedings-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:42:02Z","timestamp":1763854922000},"page":"3356-3370","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5905-4677","authenticated-orcid":false,"given":"Bo","family":"Lin","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, China and State Key Laboratory of Complex & Critical Software Environment, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1469-2063","authenticated-orcid":false,"given":"Shangwen","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China and State Key Laboratory of Complex & Critical Software Environment, ChangSha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3440-9520","authenticated-orcid":false,"given":"Yihao","family":"Qin","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China and State Key Laboratory of Complex & Critical Software Environment, ChangSha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8084-8009","authenticated-orcid":false,"given":"Liqian","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China and State Key Laboratory of Complex & Critical Software Environment, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4204-7424","authenticated-orcid":false,"given":"Xiaoguang","family":"Mao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China and State Key Laboratory of Complex & Critical Software Environment, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2012.11.007"},{"key":"e_1_3_2_1_2_1","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et al. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_2_1_3_1","unstructured":"Manish Bhatt Sahana Chennabasappa Cyrus Nikolaidis Shengye Wan Ivan Evtimov Dominik Gabi Daniel Song Faizan Ahmad Cornelius Aschermann Lorenzo Fontana et al. 2023. Purple llama cyberseceval: A secure coding benchmark for language models. arXiv preprint arXiv:2312.04724 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Efficient prompting methods for large language models: A survey. arXiv preprint arXiv:2404.01077","author":"Chang Kaiyan","year":"2024","unstructured":"Kaiyan Chang, Songcheng Xu, Chenglong Wang, Yingfeng Luo, Xiaoqian Liu, Tong Xiao, and Jingbo Zhu. 2024. Efficient prompting methods for large language models: A survey. arXiv preprint arXiv:2404.01077 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al., 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_6_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al., 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, Vol. 25, 70 (2024), 1-53.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_7_1","unstructured":"CWE Team. 2024. 2024 CWE Top 25 Most Dangerous Software Weaknesses. MITRE. https:\/\/cwe.mitre.org\/top25\/archive\/2024\/2024_cwe_top25.html"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arXiv:2401.08281 [cs.LG]","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"e_1_3_2_1_9_1","volume-title":"Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, et al.","author":"G\u00fcnther Michael","year":"2023","unstructured":"Michael G\u00fcnther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, et al., 2023. Jina embeddings 2: 8192-token general-purpose text embeddings for long documents. arXiv preprint arXiv:2310.19923 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Jaime Raldua Veuthey, and Jacob Haimes.","author":"Hariharan Suhas","year":"2024","unstructured":"Suhas Hariharan, Zainab Ali Majid, Jaime Raldua Veuthey, and Jacob Haimes. 2024. Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique. arXiv preprint arXiv:2411.08813 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.104139"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623175"},{"key":"e_1_3_2_1_13_1","volume-title":"Instruction tuning for secure code generation. 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:2402.09497 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690372"},{"key":"e_1_3_2_1_15_1","volume-title":"Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436","author":"Husain Hamel","year":"2019","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 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"Diego de Las Casas, Florian Bressand, G\u00e1bor Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q.","year":"2023","unstructured":"Albert Q. Jiang, Arthur Sablayrolles, Alexandre Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, G\u00e1bor Lengyel, Guillaume Lample, Lucile Saulnier, et al., 2023. Mistral 7B. CoRR, Vol. abs\/2310.06825 (2023). https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_2_1_17_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3661167.3661263"},{"key":"e_1_3_2_1_19_1","first-page":"39648","article-title":"Language models can solve computer tasks","volume":"36","author":"Kim Geunwoo","year":"2023","unstructured":"Geunwoo Kim, Pierre Baldi, and Stephen McAleer. 2023. Language models can solve computer tasks. Advances in Neural Information Processing Systems, Vol. 36 (2023), 39648-39677.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690283"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643795.3648384"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680371"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690635"},{"key":"e_1_3_2_1_24_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation. arXiv preprint arXiv:2502.03233","author":"Lin Bo","year":"2025","unstructured":"Bo Lin, Shangwen Wang, Liqian Chen, and Xiaoguang Mao. 2025. Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation. arXiv preprint arXiv:2502.03233 (2025)."},{"key":"e_1_3_2_1_26_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_28_1","unstructured":"Microsoft. 2024. Retrieval-Augmented Generation (RAG) in Azure Machine Learning. https:\/\/learn.microsoft.com\/en-us\/azure\/machine-learning\/concept-retrieval-augmented-generation"},{"key":"e_1_3_2_1_29_1","unstructured":"MITRE Corporation. [n.d.]. Common Vulnerabilities and Exposures (CVE). https:\/\/cve.mitre.org\/."},{"key":"e_1_3_2_1_30_1","volume-title":"Sosecure: Safer code generation with rag and stackoverflow discussions. arXiv:2503.13654","author":"Mukherjee Manisha","year":"2025","unstructured":"Manisha Mukherjee and Vincent J Hellendoorn. 2025. Sosecure: Safer code generation with rag and stackoverflow discussions. arXiv:2503.13654 (2025)."},{"key":"e_1_3_2_1_31_1","unstructured":"Ollama. 2023. Ollama framework. https:\/\/ollama.com\/."},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. [n.d.]. GPT-4o. https:\/\/platform.openai.com\/docs\/models#gpt-4."},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2024. ChatGPT Retrieval Plugin. https:\/\/github.com\/openai\/chatgpt-retrieval-plugin"},{"key":"e_1_3_2_1_34_1","volume-title":"An empirical study of the non-determinism of chatgpt in code generation. ACM Transactions on Software Engineering and Methodology","author":"Ouyang Shuyin","year":"2024","unstructured":"Shuyin Ouyang, Jie M Zhang, Mark Harman, and Meng Wang. 2024. An empirical study of the non-determinism of chatgpt in code generation. ACM Transactions on Software Engineering and Methodology (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"e_1_3_2_1_36_1","volume-title":"From sparse to soft mixtures of experts. arXiv preprint arXiv:2308.00951","author":"Puigcerver Joan","year":"2023","unstructured":"Joan Puigcerver, Carlos Riquelme, Basil Mustafa, and Neil Houlsby. 2023. From sparse to soft mixtures of experts. arXiv preprint arXiv:2308.00951 (2023)."},{"key":"e_1_3_2_1_37_1","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis. arXiv:2009.10297 [cs.SE]"},{"key":"e_1_3_2_1_38_1","volume-title":"Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al., 2023. Code llama: Open foundation models for code. arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_39_1","unstructured":"Semgrep Inc. 2025. Semgrep. https:\/\/semgrep.dev\/."},{"key":"e_1_3_2_1_40_1","volume-title":"Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, et al.","author":"Sturua Saba","year":"2024","unstructured":"Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, et al., 2024. jina-embeddings-v3: Multilingual embeddings with task lora. arXiv preprint arXiv:2409.10173 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.143"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-024-10590-1"},{"key":"e_1_3_2_1_43_1","volume-title":"Markus Mutas, Salem Dhiff, and Riccardo Scandariato.","author":"Tony Catherine","year":"2024","unstructured":"Catherine Tony, Nicol\u00e1s E D\u00edaz Ferreyra, Markus Mutas, Salem Dhiff, and Riccardo Scandariato. 2024. Prompting techniques for secure code generation: A systematic investigation. ACM Trans. Softw. Eng. Methodol. (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR59073.2023.00084"},{"key":"e_1_3_2_1_45_1","unstructured":"Shengye Wan Cyrus Nikolaidis Daniel Song David Molnar James Crnkovich Jayson Grace Manish Bhatt Sahana Chennabasappa Spencer Whitman Stephanie Ding et al. 2024. Cyberseceval 3: Advancing the evaluation of cybersecurity risks and capabilities in large language models. arXiv preprint arXiv:2408.01605 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Is your ai-generated code really safe? evaluating large language models on secure code generation with codeseceval. arXiv preprint arXiv:2407.02395","author":"Wang Jiexin","year":"2024","unstructured":"Jiexin Wang, Xitong Luo, Liuwen Cao, Hongkui He, Hailin Huang, Jiayuan Xie, Adam Jatowt, and Yi Cai. 2024b. Is your ai-generated code really safe? evaluating large language models on secure code generation with codeseceval. arXiv preprint arXiv:2407.02395 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639478.3647634"},{"key":"e_1_3_2_1_48_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_49_1","unstructured":"Felix Wilhelm Fabian Freyer Calle Svensson Thomas Otto Michal Melewski William Woodruff Disconnect3d and Matthew Rinaldi. 2025. weggli. https:\/\/github.com\/weggli-rs\/weggli."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1927.10502953"},{"key":"e_1_3_2_1_51_1","volume-title":"Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities. ACM Transactions on Software Engineering and Methodology","author":"Yang Zezhou","year":"2025","unstructured":"Zezhou Yang, Sirong Chen, Cuiyun Gao, Zhenhao Li, Xing Hu, Kui Liu, and Xin Xia. 2025. An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities. ACM Transactions on Software Engineering and Methodology (2025)."},{"key":"e_1_3_2_1_53_1","unstructured":"Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu et al. 2023a. Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.90"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534387"},{"key":"e_1_3_2_1_56_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_57_1","unstructured":"Qihao Zhu Daya Guo Zhihong Shao Dejian Yang Peiyi Wang Runxin Xu Y Wu Yukun Li Huazuo Gao Shirong Ma et al. 2024. DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence. arXiv preprint arXiv:2406.11931 (2024)."}],"event":{"name":"CCS '25: ACM SIGSAC Conference on Computer and Communications Security","location":"Taipei Taiwan","acronym":"CCS '25","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719027.3765049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:27:01Z","timestamp":1766442421000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719027.3765049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":57,"alternative-id":["10.1145\/3719027.3765049","10.1145\/3719027"],"URL":"https:\/\/doi.org\/10.1145\/3719027.3765049","relation":{},"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}