SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement

Authors: Yi Chen, Yun Bian, Haiquan Wang, Shihao Li, Zhe Cui
Published: 2026-03-09

Source: https://arxiv.org/abs/2603.08520

PDF: https://arxiv.org/pdf/2603.08520

AIにより推定されたラベル

脆弱性評価 LLM性能評価 プログラム解析

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments on three mainstream LLMs, this paper reveals the iterative refinement paradox: specification drift during multi-objective optimization causes security to degrade gradually over successive iterations. Taking GPT-4o as an example, 43.7