Cover Image

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Naizhu, Li, Zhong, Zhang, Tian, Zeng, Qingkai
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation
by: Jin, Naizhu, et al.
Published: (2024)

MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages
by: Jin, Naizhu, et al.
Published: (2025)

Understanding Chain-of-Thought Effectiveness in Code Generation: An Empirical and Information-Theoretic Analysis
by: Jin, Naizhu, et al.
Published: (2025)

Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs
by: Zhu, Yuqi, et al.
Published: (2025)

Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models
by: Yang, Guang, et al.
Published: (2023)

Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
by: Yang, Guang, et al.
Published: (2026)

GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation
by: Li, Jia, et al.
Published: (2025)

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
by: Zhang, Kechi, et al.
Published: (2024)

SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
by: Gao, Shuzheng, et al.
Published: (2025)

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

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision
by: Lu, Xu, et al.
Published: (2025)

Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation
by: Ye, Junyao, et al.
Published: (2025)

SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking
by: Ma, Hongru, et al.
Published: (2025)

Multi-Agent Code-Orchestrated Generation for Reliable Infrastructure-as-Code
by: Khan, Rana Nameer Hussain, et al.
Published: (2025)

LaTCoder: Converting Webpage Design to Code with Layout-as-Thought
by: Gui, Yi, et al.
Published: (2025)

CodeAgent: Autonomous Communicative Agents for Code Review
by: Tang, Xunzhu, et al.
Published: (2024)

Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
by: Xiong, Qian, et al.
Published: (2025)

A Multi-agent Onboarding Assistant based on Large Language Models, Retrieval Augmented Generation, and Chain-of-Thought
by: Ionescu, Andrei Cristian, et al.
Published: (2025)

Uncovering Weaknesses in Neural Code Generation
by: Lian, Xiaoli, et al.
Published: (2024)

A Survey on Code Generation with LLM-based Agents
by: Dong, Yihong, et al.
Published: (2025)

VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
by: Le, Cuong Chi, et al.
Published: (2024)

Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents
by: Liu, Zihan, et al.
Published: (2024)

An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains
by: Yan, Zihe, et al.
Published: (2025)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
by: Guo, Chengquan, et al.
Published: (2024)

ReVul-CoT: Towards Effective Software Vulnerability Assessment with Retrieval-Augmented Generation and Chain-of-Thought Prompting
by: Chen, Zhijie, et al.
Published: (2025)

Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks
by: Mohseni, Seyedreza, et al.
Published: (2026)

CodeScore: Evaluating Code Generation by Learning Code Execution
by: Dong, Yihong, et al.
Published: (2023)

Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
by: Li, Xiang, et al.
Published: (2026)

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code
by: Zhang, Kechi, et al.
Published: (2024)

RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation
by: Liu, Yang, et al.
Published: (2025)

Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging
by: Hua, Ziyue, et al.
Published: (2026)

Inducing Vulnerable Code Generation in LLM Coding Assistants
by: Zeng, Binqi, et al.
Published: (2025)

BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks
by: Xiao, Yisong, et al.
Published: (2024)

CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
by: Pan, Ruwei, et al.
Published: (2025)

Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
by: Zhang, Wei, et al.
Published: (2024)

Backdoors in Code Summarizers: How Bad Is It?
by: Wang, Chenyu, et al.
Published: (2025)

Fixing Large Language Models' Specification Misunderstanding for Better Code Generation
by: Tian, Zhao, et al.
Published: (2023)

On the Effectiveness of Training Data Optimization for LLM-based Code Generation: An Empirical Study
by: Kuang, Shiqi, et al.
Published: (2025)

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
by: Li, Qingyao, et al.
Published: (2024)

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
by: Guo, Chengquan, et al.
Published: (2025)