用大模型生成或重构漏洞代码，提升分类器性能
LLM-based Vulnerable Code Augmentation: Generate or Refactor?
- 对比生成新漏洞代码与重构现有代码两种方式
- 混合策略使分类器准确率显著提升
- 适合做漏洞检测数据增强的研究者使用
漏洞代码库常存在严重不平衡问题，限制了基于深度学习的漏洞分类器效果。数据增强可通过缓解低频漏洞类型的稀缺性来改善这一问题。本文研究基于大模型的漏洞函数增强方法，比较了可控生成新漏洞样本与保持语义的现有样本重构两种策略。利用Qwen2.5-Coder生成增强数据，以CodeBERT作为分类器，在SVEN数据集上验证表明，该方法能通过简单流程有效丰富漏洞代码库，且质量合理；混合策略可最佳提升分类器性能。代码仓库已公开。
原文摘要 · Abstract (English)
Vulnerability code-bases often suffer from severe imbalance, limiting the effectiveness of Deep Learning-based vulnerability classifiers. Data Augmentation could help solve this by mitigating the scarcity of under-represented vulnerability types. In this context, we investigate LLM-based augmentation for vulnerable functions, comparing controlled generation of new vulnerable samples with semantics-preserving refactoring of existing ones. Using Qwen2.5-Coder to produce augmented data and CodeBERT as a classifier on the SVEN dataset, we find that our approaches are indeed effective in enriching vulnerable code-bases through a simple process and with reasonable quality, and that a hybrid strategy best boosts vulnerability classifiers' performance. Code repository is available here : https://github.com/DynaSoumhaneOuchebara/LLM-based-code-augmentation-Generate-or-Refactor-
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。