{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T22:08:57Z","timestamp":1790287737527,"version":"4.1.0"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tse.2026.3689066","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:47:37Z","timestamp":1777578457000},"page":"2250-2267","source":"Crossref","is-referenced-by-count":6,"title":["Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation"],"prefix":"10.1109","volume":"52","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","place":["Changsha, China"],"department":["College of Computer Science"]}],"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","place":["Changsha, China"],"department":["College of Computer Science"]}],"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","place":["Changsha, China"],"department":["College of Computer Science"]}],"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","place":["Changsha, China"],"department":["College of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Benchmark self-evolving: A multi-agent framework for dynamic LLM evaluation","author":"Wang","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510203"},{"key":"ref3","first-page":"65","article-title":"Preference-guided refactored tuning for retrieval augmented code generation","volume-title":"Proc. 39th IEEE\/ACM Int. Conf. Automated Softw. Eng.","author":"Gao","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.176"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.232"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00179"},{"key":"ref7","article-title":"Connecting github to chatgpt: Deep research","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-024-10590-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690283"},{"key":"ref11","article-title":"Retrieval-augmented generation (RAG) in azure machine learning","year":"2024"},{"key":"ref12","article-title":"Chatgpt retrieval plugin","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.143"},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2025.112727"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-026-60308-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref19","article-title":"Code Llama: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"ref20","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1899"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.590"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.558"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"4420","DOI":"10.18653\/v1\/2024.acl-long.242","article-title":"Small models, big insights: Leveraging slim proxy models to decide when and what to retrieve for LLMs","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Tan","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.banglalp-1.15"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.194"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5121\/ijnlc.2024.13103"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616256"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.90"},{"key":"ref33","first-page":"1831","article-title":"Formalizing and benchmarking prompt injection attacks and defenses","volume-title":"Proc. 33rd USENIX Secur. Symp. (USENIX)","author":"Liu","year":"2024"},{"key":"ref34","article-title":"From prompt injections to SQL injection attacks: How protected is your LLM-integrated web application?","author":"Pedro","year":"2023"},{"key":"ref35","article-title":"Ignore previous prompt: Attack techniques for language models","author":"Perez","year":"2022"},{"key":"ref36","article-title":"Prompt injection attacks and defenses in LLM-integrated applications","author":"Liu","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.272"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30150"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24188"},{"key":"ref40","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"ref41","first-page":"995","article-title":"RMCBench: Benchmarking large language models\u2019 resistance to malicious code","volume-title":"Proc. 39th IEEE\/ACM Int. Conf. Automated Softw. Eng.","author":"Chen","year":"2024"},{"key":"ref42","first-page":"6106","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume":"31","author":"Shafahi","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref43","article-title":"Poisoning attacks against support vector machines","author":"Biggio","year":"2012"},{"key":"ref44","article-title":"PoisonedRAG: Knowledge poisoning attacks to retrieval-augmented generation of large language models","author":"Zou","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3717061"},{"key":"ref46","article-title":"4.5 million (suspected) fake stars in Github: A growing spiral of popularity contests, scams, and malware","author":"He","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583503"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23291"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3264418"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387501"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3475960.3475985"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP52600.2021.00020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3607199.3607242"},{"key":"ref54","article-title":"Go-ethereum: Official go implementation of the ethereum protocol","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.345"},{"key":"ref56","article-title":"National vulnerability database (NVD)","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3639478.3647634"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3087402"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.6028\/jres.123.005"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1145\/3377811.3380364","article-title":"Empirical review of automated analysis tools on 47,587 ethereum smart contracts","volume-title":"Proc. ACM\/IEEE 42nd Int. Conf. Softw. Eng.","author":"Durieux","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397385"},{"key":"ref62","article-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3699711"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608134"},{"issue":"14","key":"ref65","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Prob., Oakland, CA, USA","volume":"1","author":"MacQueen","year":"1967"},{"issue":"9","key":"ref66","first-page":"17","article-title":"EBK-means: A clustering technique based on elbow method and k-means in wsn","volume":"105","author":"Bholowalia","year":"2014","journal-title":"Int. J. Comput. Appl."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2966182"},{"issue":"1","key":"ref68","first-page":"5","article-title":"Introduction to the K-means clustering algorithm based on the elbow method","volume":"1","author":"Cui","year":"2020","journal-title":"Account. Audit. Finance"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/336\/1\/012017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680313"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.306"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LLM4Code66737.2025.00009"},{"key":"ref74","article-title":"CodeQL","year":"2025"},{"key":"ref75","article-title":"LLM safety leaderboard","year":"2024"},{"key":"ref76","article-title":"GPT-4O"},{"key":"ref77","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref78","article-title":"DeepSeek-Coder-V2: Breaking the barrier of closed-source models in code intelligence","author":"Zhu","year":"2024"},{"key":"ref79","article-title":"OpenAI API reference\u2014Chat create N","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref82","article-title":"Jina-embeddings-V3: Multilingual embeddings with task lora","author":"Sturua","year":"2024"},{"key":"ref83","article-title":"OpenAI models\u2014Embeddings","year":"2024"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556903"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref86","article-title":"Ollama framework","year":"2023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3697010"},{"key":"ref88","article-title":"DeepSeek v2.5","year":"2024"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53992.2023.10394237"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3582688"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref92","article-title":"2024 CWE top 25 most dangerous software weaknesses","year":"2024"},{"issue":"9","key":"ref93","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3480027","article-title":"Opportunities and challenges in code search tools","volume":"54","author":"Liu","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3403042"},{"key":"ref95","article-title":"HijackRAG: Hijacking attacks against retrieval-augmented large language models","author":"Zhang","year":"2024"},{"key":"ref96","article-title":"GitHub language statistics (GitHut)","year":"2024"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11655897\/11502011.pdf?arnumber=11502011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T05:17:45Z","timestamp":1786771065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11502011\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":96,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tse.2026.3689066","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}