{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-exploratory-study-on-fine-tuning-large","title":"An Exploratory Study on Fine-Tuning Large Language Models for Secure Code Generation","arxiv_id":"2408.09078","date":"2024-08-17","proceeding":null,"authors":["Junjie Li","Fazle Rabbi","Cheng Cheng","Aseem Sangalay","Yuan Tian","Jinqiu Yang"],"abstract":"AI-powered coding assistants such as GitHub's Copilot and OpenAI's ChatGPT have achieved notable success in automating code generation. However, these tools rely on pre-trained Large Language Models (LLMs) that are typically trained on human-written code sourced from open-source project hosting sites like GitHub, which often contains inherent security vulnerabilities. These vulnerabilities may then be mirrored in the code generated by these LLMs, a critical risk revealed and highlighted by recent empirical studies. In this work, we present an exploratory study on whether fine-tuning pre-trained LLMs on datasets of vulnerability-fixing commits can promote secure code generation. We explored full fine-tuning and two parameter-efficient fine-tuning techniques (LoRA and IA3) on four pre-trained LLMs for code generation. We crawled a fine-tuning dataset (14,622 C/C++ files) for secure code generation by collecting code fixes of confirmed vulnerabilities from open-source repositories. Our evaluation dataset comprises 52 vulnerability scenarios designed to cover the top most dangerous C/C++ CWEs. Our exploration reveals that fine-tuning LLMs using PEFT techniques can enhance secure code generation. We observe maximum improvements in security of 6.4% in C language and 5.0% in C++ language. In addition, we compared between the fine-tuning approaches and the prompt-based approaches. The LoRA-tuned models outperform the prompt-based approaches in secure code generation. We found that fine-tuning with function-level and block-level datasets achieves the best secure code generation performance, compared to the alternatives (file-level and line-level).","url_abs":"https://arxiv.org/abs/2408.09078v1","url_pdf":"https://arxiv.org/pdf/2408.09078v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"an-exploratory-study-on-fine-tuning-large","repo_url":"https://github.com/SecureLLM/Secure_LLM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.09078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09078"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SecureLLM/Secure_LLM","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"19ee4683eda506c6","entry":"list_of_strings","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"19ee4683eda506c6"}},{"code_sha256_prefix":"a51187f2a76ed738","entry":"propose_prompt","repo":"SecureLLM/Secure_LLM","repo_kind":"official","path":"code_generation/generate.py","file_url":"https://github.com/SecureLLM/Secure_LLM/blob/HEAD/code_generation/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a51187f2a76ed738"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}