Llama-based source code vulnerability detection: Prompt engineering vs Fine tuning

• URL: http://arxiv.org/abs/2512.09006v1
• Date: Tue, 09 Dec 2025 12:08:24 GMT
• Title: Llama-based source code vulnerability detection: Prompt engineering vs Fine tuning
• Authors: Dyna Soumhane Ouchebara, Stéphane Dupont,
• Abstract summary: Large Language Models (LLMs) are considered among the most performant AI models to date.<n>We study their performance and apply different state-of-the-art techniques to enhance their effectiveness.<n>We leverage the recent open-source Llama-3.1 8B, with source code samples extracted from BigVul and PrimeVul datasets.
• Score: 0.6588840794922407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The significant increase in software production, driven by the acceleration of development cycles over the past two decades, has led to a steady rise in software vulnerabilities, as shown by statistics published yearly by the CVE program. The automation of the source code vulnerability detection (CVD) process has thus become essential, and several methods have been proposed ranging from the well established program analysis techniques to the more recent AI-based methods. Our research investigates Large Language Models (LLMs), which are considered among the most performant AI models to date, for the CVD task. The objective is to study their performance and apply different state-of-the-art techniques to enhance their effectiveness for this task. We explore various fine-tuning and prompt engineering settings. We particularly suggest one novel approach for fine-tuning LLMs which we call Double Fine-tuning, and also test the understudied Test-Time fine-tuning approach. We leverage the recent open-source Llama-3.1 8B, with source code samples extracted from BigVul and PrimeVul datasets. Our conclusions highlight the importance of fine-tuning to resolve the task, the performance of Double tuning, as well as the potential of Llama models for CVD. Though prompting proved ineffective, Retrieval augmented generation (RAG) performed relatively well as an example selection technique. Overall, some of our research questions have been answered, and many are still on hold, which leaves us many future work perspectives. Code repository is available here: https://github.com/DynaSoumhaneOuchebara/Llama-based-vulnerability-detection.

Related papers

• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [78.09559830840595]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• Machine Learning Pipeline for Software Engineering: A Systematic Literature Review [0.0]
  This systematic literature review examines state-of-the-art Machine Learning pipelines designed for software engineering (SE)<n>Our findings show that robust preprocessing, such as SMOTE for data balancing, improves model reliability.<n> Ensemble methods like Random Forest and Gradient Boosting dominate performance across tasks.<n>New metrics like Best Arithmetic Mean (BAM) are emerging in niche applications.
  arXiv  Detail & Related papers  (2025-07-31T15:37:30Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models [2.171120568435925]
  Large Language Models (LLMs) for code require significant computational resources for training and fine-tuning.<n>To address this, the research community has increasingly turned to Efficient Fine-Tuning (PEFT)<n>PEFT enables the adaptation of large models by updating only a small subset of parameters, rather than the entire model.<n>Our study synthesizes findings from 28 peer-reviewed papers, identifying patterns in configuration strategies and adaptation trade-offs.
  arXiv  Detail & Related papers  (2025-04-29T16:19:25Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We? [8.0988059417354]
  We propose a range of approaches to improve the performance of AI-generated code detection. Our best model outperforms state-of-the-art AI-generated code detector (GPTSniffer) and achieves an F1 score of 82.55.
  arXiv  Detail & Related papers  (2024-11-06T22:48:18Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• SCoPE: Evaluating LLMs for Software Vulnerability Detection [0.0]
  This work explores and refines the CVEFixes dataset, which is commonly used to train models for code-related tasks. The output generated by SCoPE was used to create a new version of CVEFixes. The results show that SCoPE successfully helped to identify 905 duplicates within the evaluated subset.
  arXiv  Detail & Related papers  (2024-07-19T15:02:00Z)
• Cross Project Software Vulnerability Detection via Domain Adaptation and Max-Margin Principle [21.684043656053106]
  Software vulnerabilities (SVs) have become a common, serious and crucial concern due to the ubiquity of computer software. We propose a novel end-to-end approach to tackle these two crucial issues. Our method obtains a higher performance on F1-measure, the most important measure in SVD, from 1.83% to 6.25% compared to the second highest method in the used datasets.
  arXiv  Detail & Related papers  (2022-09-19T23:47:22Z)
• Few-shot Quality-Diversity Optimization [50.337225556491774]
  Quality-Diversity (QD) optimization has been shown to be effective tools in dealing with deceptive minima and sparse rewards in Reinforcement Learning. We show that, given examples from a task distribution, information about the paths taken by optimization in parameter space can be leveraged to build a prior population, which when used to initialize QD methods in unseen environments, allows for few-shot adaptation. Experiments carried in both sparse and dense reward settings using robotic manipulation and navigation benchmarks show that it considerably reduces the number of generations that are required for QD optimization in these environments.
  arXiv  Detail & Related papers  (2021-09-14T17:12:20Z)
• Anomaly Detection Based on Selection and Weighting in Latent Space [73.01328671569759]
  We propose a novel selection-and-weighting-based anomaly detection framework called SWAD. Experiments on both benchmark and real-world datasets have shown the effectiveness and superiority of SWAD.
  arXiv  Detail & Related papers  (2021-03-08T10:56:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.