{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:51:30Z","timestamp":1772934690791,"version":"3.50.1"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2421324"],"award-info":[{"award-number":["2421324"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401846","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"4343-4352","source":"Crossref","is-referenced-by-count":0,"title":["A Survey on the Role of LLMs in AI-Based Software Development: Augmentation and Latent Risks"],"prefix":"10.1109","author":[{"given":"Md Bajlur","family":"Rashid","sequence":"first","affiliation":[{"name":"University of West Florida,Department of Cybersecurity and Information Technology,USA"}]},{"given":"Mohammad Shafayet Jamil","family":"Hossain","sequence":"additional","affiliation":[{"name":"South Dakota State University,Department of Mathematics and Statistics,South Dakota,USA"}]},{"given":"Mohammad Ishtiaque","family":"Khan","sequence":"additional","affiliation":[{"name":"Kennesaw State University,Department of Computer Science,Georgia,USA"}]},{"given":"Sharaban","family":"Tahora","sequence":"additional","affiliation":[{"name":"Kennesaw State University,Department of Computer Science,Georgia,USA"}]},{"given":"Aiasha","family":"Siddika","sequence":"additional","affiliation":[{"name":"Georgia Gwinnett College,Information Technology,USA"}]},{"given":"Mahmudul Islam","family":"Prakash","sequence":"additional","affiliation":[{"name":"University of West Florida,Department of Mathematics Statistics,USA"}]},{"given":"Sharmin","family":"Yeasmin","sequence":"additional","affiliation":[{"name":"Southeast University,Department of Computer Science,Bangladesh"}]},{"given":"Hossain","family":"Shahriar","sequence":"additional","affiliation":[{"name":"University of West Florida,Center for Cybersecurity,Florida,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Code llama: Open foundation models for code","author":"Rozi\u00e8re","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref7","article-title":"Graphcodebert: Pre-training code representations with data flow","author":"Guo","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Vulnllmeval: A framework for evaluating large language models in software vulnerability detection and patching","author":"Zibaeirad","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.212"},{"key":"ref11","volume-title":"Evaluating large language models in ransomware negotiation: A comparative analysis of chatgpt and claude","author":"Kumamoto","year":"2023"},{"key":"ref12","article-title":"Scgagent: Recreating the benefits of reasoning models for secure code generation with agentic workflows","author":"Saul","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3541146"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3769082"},{"key":"ref15","volume-title":"Code vulnerability detection: A comparative analysis of emerging large language models","author":"Sultana","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC65507.2025.00135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC65507.2025.00129"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/dasc68382.2025.00017"},{"key":"ref19","volume-title":"A survey of large language models","author":"Zhao","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3744553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3716848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3716848"},{"key":"ref24","article-title":"Large language models and code security: A systematic literature review","author":"Basic","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/saner60148.2024.00051"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-68738-9_34"},{"key":"ref27","volume-title":"Data Security and Privacy Concerns for Generative AI Platforms","author":"Tomassi","year":"2024"},{"key":"ref28","article-title":"Extracting training data from large language models","author":"Carlini","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LLM4Code66737.2025.00018"},{"key":"ref30","article-title":"Everything you wanted to know about 11 m -based vulnerability detection but were afraid to ask","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref31","volume-title":"Badgpt: Exploring security vulnerabilities of chatgpt via backdoor attacks to instructgpt","author":"Shi","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3641540"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/568760.568869"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10888-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2024.1386720"},{"key":"ref37","volume-title":"Llm-used: Repository of 11 m framework usage data and plots.","author":"Hossain","year":"2025"},{"key":"ref38","first-page":"35","article-title":"Modeling adaptive hypermedia with an object-oriented approach and xml","volume":"2002","author":"Cannataro","year":"2002","journal-title":"WebDyn@ WWW"},{"key":"ref39","article-title":"Can we trust large language models generated code? a framework for in-context learning, security patterns, and code evaluations across diverse 11 ms","author":"Mohsin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3708519"},{"issue":"2007","key":"ref41","first-page":"1","article-title":"Guidelines for performing systematic literature reviews in software engineering","volume":"2","author":"Kitchenham","year":"2007","journal-title":"EBSE Technical Report"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34537"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3716848"},{"key":"ref44","volume-title":"Artificial-intelligence generated code considered harmful: A road map for secure and high-quality code generation","author":"Chong","year":"2024"},{"key":"ref45","first-page":"1","article-title":"Human-ai collaboration in secure software engineering: Opportunities and challenges","volume":"29","author":"Zhang","year":"2024","journal-title":"Empirical Software Engineering"},{"key":"ref46","first-page":"50","article-title":"A probabilistic approach to model adaptive hypermedia systems","author":"Cannataro","year":"2001","journal-title":"WebDyn @ ICDT"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SANER60148.2024.00051"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/DSD67783.2025.00087"},{"key":"ref49","article-title":"Evaluating the performance of the deepseek model in confidential computing environment","author":"Dong","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1490"},{"key":"ref51","volume-title":"Secure software development practices for generative ai and dual-use foundation models: An ssdf community profile (sp 800\u2013218a).","year":"2024"},{"key":"ref52","first-page":"2205","article-title":"Lost at c: A user study on the security implications of large language model code assistants","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Sandoval"},{"key":"ref53","volume-title":"Sok: Towards effective automated vulnerability repair","author":"Li","year":"2025"},{"key":"ref54","article-title":"Longitudinal studies of ai in safetycritical systems: Lessons for software security","author":"Smith","year":"2025","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISTAS65609.2025.11269659"},{"key":"ref56","article-title":"Prompt flow integrity to prevent privilege escalation in 11 m agents","volume-title":"Proceedings of the 2025 Conference on Machine Learning and Security","author":"Kim","year":"2025"},{"key":"ref57","article-title":"Llm-assisted malware generation: Risks and defenses","volume-title":"Proceedings of the IEEE Symposium on Security and Privacy Workshops","author":"Xu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3482719"},{"key":"ref59","volume-title":"Lessleak-bench: A first investigation of data leakage in 11 ms across 83 software engineering benchmarks","author":"Zhou","year":"2025"},{"key":"ref60","article-title":"When developer aid becomes security debt: A systematic analysis of insecure behaviors in 11 m coding agents","author":"Kozak","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref61","volume-title":"Toward trustworthy ai development: Mechanisms for supporting verifiable claims","author":"Brundage","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-008-0065-4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ISADS.2003.1193935"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3607199.3607242"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401846.pdf?arnumber=11401846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:14:47Z","timestamp":1772867687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401846","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}