Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yi, Bian, Yun, Wang, Haiquan, Li, Shihao, Cui, Zhe
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM Security Guard for Code
by: Kavian, Arya, et al.
Published: (2024)

Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection
by: Bian, Yun, et al.
Published: (2026)

How to Compare the Security of Code Written by Humans to LLM-generated Code
by: Balebako, Rebecca, et al.
Published: (2026)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
by: Tessa, Melissa, et al.
Published: (2026)

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code
by: Elsayed, Mohamed, et al.
Published: (2026)

Generating API Parameter Security Rules with LLM for API Misuse Detection
by: Liu, Jinghua, et al.
Published: (2024)

Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
by: Hasan, Mohammad Saqib, et al.
Published: (2025)

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
by: Xiao, Yuan, et al.
Published: (2026)

Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
by: Lin, Bo, et al.
Published: (2025)

Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation
by: Li, Tian, et al.
Published: (2025)

Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation
by: Lin, Bo, et al.
Published: (2025)

Security of Language Models for Code: A Systematic Literature Review
by: Chen, Yuchen, et al.
Published: (2024)

From Detection to Prevention: Explaining Security-Critical Code to Avoid Vulnerabilities
by: Krishnamurthy, Ranjith, et al.
Published: (2026)

Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
by: Fu, Yujia, et al.
Published: (2023)

Security Incentivization: An Empirical Study of how Micropayments Impact Code Security
by: Rass, Stefan, et al.
Published: (2026)

RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories
by: Wang, Yanlin, et al.
Published: (2026)

SecCodePRM: A Process Reward Model for Code Security
by: Yu, Weichen, et al.
Published: (2026)

Secure Coding with AI -- From Detection to Repair
by: Belozerov, Vladislav, et al.
Published: (2025)

MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
by: Wang, Shenao, et al.
Published: (2024)

Exploring Security Practices in Infrastructure as Code: An Empirical Study
by: Verdet, Alexandre, et al.
Published: (2023)

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code
by: Ning, Kaiwen, et al.
Published: (2024)

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
by: Weng, Shihao, et al.
Published: (2026)

How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
by: Chen, Maofei, et al.
Published: (2026)

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
by: Xu, Hanxiang, et al.
Published: (2024)

Security of LLM-generated Code: A Comparative Analysis
by: Morkonda, Srivathsan G, et al.
Published: (2026)

Probing Privacy Leaks in LLM-based Code Generation via Test Generation
by: Ge, Yifei, et al.
Published: (2026)

LLM4CVE: Enabling Iterative Automated Vulnerability Repair with Large Language Models
by: Fakih, Mohamad, et al.
Published: (2025)

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs
by: Yuan, He Yang, et al.
Published: (2026)

GenSIaC: Toward Security-Aware Infrastructure-as-Code Generation with Large Language Models
by: Li, Yikun, et al.
Published: (2025)

CodableLLM: Automating Decompiled and Source Code Mapping for LLM Dataset Generation
by: Manuel, Dylan, et al.
Published: (2025)

MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization
by: Lu, Haolang, et al.
Published: (2024)

Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices
by: Patir, Rupam, et al.
Published: (2025)

Does Teaming-Up LLMs Improve Secure Code Generation? A Comprehensive Evaluation with Multi-LLMSecCodeEval
by: Sabir, Bushra, et al.
Published: (2026)

Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
by: Li, Ying, et al.
Published: (2026)

Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox
by: Shukla, Shivani, et al.
Published: (2025)

The Kubernetes Security Landscape: AI-Driven Insights from Developer Discussions
by: Curtis, J. Alexander, et al.
Published: (2024)

Assessing Vulnerability in Smart Contracts: The Role of Code Complexity Metrics in Security Analysis
by: Tehrani, Masoud Jamshidiyan
Published: (2024)

LibScan: Smart Contract Library Misuse Detection with Iterative Feedback and Static Verification
by: Wang, Yishun, et al.
Published: (2026)

Large Language Models for Secure Code Assessment: A Multi-Language Empirical Study
by: Dozono, Kohei, et al.
Published: (2024)

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
by: Li, Yue, et al.
Published: (2026)