paper-with-me

홈 › Papers

Synthetic Code Surgery: Repairing Bugs and Vulnerabilities with LLMs and Synthetic Data

2025-05-12 · David de-Fitero-Dominguez, Antonio Garcia-Cabot, Eva Garcia-Lopez

This paper presents a novel methodology for enhancing Automated Program Repair (APR) through synthetic data generation utilizing Large Language Models (LLMs). Current APR systems are constrained by the limited availability of high-quality training data encompassing diverse bug types across multiple programming languages. The proposed approach addresses this limitation through a two-phase process: a synthetic sample generation followed by a rigorous quality assessment. Multiple state-of-the-art LLMs were employed to generate approximately 30,000 paired examples of buggy and fixed code across 12 programming languages and 13 bug categories. Subsequently, these samples underwent cross-model evaluation against five criteria: correctness, code quality, security, performance, and completeness. Experimental evaluation on the VulRepair test set dataset showed statistically significant improvements in Perfect Prediction rates, with the quality-filtered synthetic dataset outperforming both baseline and real-world commit data configurations in certain scenarios. The methodology was validated through rigorous statistical testing, including ANOVA and post-hoc Tukey's Honest Significant Difference analysis. Furthermore, the best-performing configurations surpassed existing systems despite using a less computationally intensive decoding strategy. This research establishes a self-bootstrapping paradigm in which LLMs generate and evaluate their own training data, potentially transforming approaches to data scarcity across software engineering tasks and advancing the development of robust, adaptable tools for automated code maintenance.

📄 PDF Abstract BibTeX arXiv:2505.07372

Code (0)

등록된 구현이 없습니다.

Tasks

Program RepairSynthetic Data Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Logical Segmentation of Source Code

2019-07-18 · Jacob Dormuth, Ben Gelman, Jessica Moore, David Slater

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing…

Segmentation

DREAM: Debugging and Repairing AutoML Pipelines

2023-12-31 · XiaoYu Zhang, Juan Zhai, Shiqing Ma, Chao Shen

Deep Learning models have become an integrated component of modern software systems. In response to the challenge of model design, researchers proposed Automated Machine Learning (AutoML) systems, which automatically sea…

AutoML

LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software

2026-04-14 · Syed Md Mukit Rashid, Abdullah Al Ishtiaq, Kai Tu, Yilu Dong 외 arxiv

Logical vulnerabilities in software stem from flaws in program logic rather than memory safety, which can lead to critical security failures. Although existing automated program repair techniques primarily focus on repai…

Program Repair

Neural Transfer Learning for Repairing Security Vulnerabilities in C Code

2021-04-16 · Zimin Chen, Steve Kommrusch, Martin Monperrus

In this paper, we address the problem of automatic repair of software vulnerabilities with deep learning. The major problem with data-driven vulnerability repair is that the few existing datasets of known confirmed vulne…

Bug fixingC++ codeDenoisingTransfer Learning

BugSweeper: Function-Level Detection of Smart Contract Vulnerabilities Using Graph Neural Networks

2025-12-10 · Uisang Lee, Changhoon Chung, Junmo Lee, Soo-Mook Moon arxiv

The rapid growth of Ethereum has made it more important to quickly and accurately detect smart contract vulnerabilities. While machine-learning-based methods have shown some promise, many still rely on rule-based preproc…

Graph Neural Network