Image de couverture de livre

SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jin, Naizhu, Li, Zhong, Guo, Yinggang, Su, Chao, Zhang, Tian, Zeng, Qingkai
Format:	Preprint
Publié:	2024
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation
par: Jin, Naizhu, et autres
Publié: (2025)

MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages
par: Jin, Naizhu, et autres
Publié: (2025)

Understanding Chain-of-Thought Effectiveness in Code Generation: An Empirical and Information-Theoretic Analysis
par: Jin, Naizhu, et autres
Publié: (2025)

Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models
par: Yang, Guang, et autres
Publié: (2023)

Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs
par: Zhu, Yuqi, et autres
Publié: (2025)

Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation
par: Ye, Junyao, et autres
Publié: (2025)

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
par: Chang, Shuyu, et autres
Publié: (2026)

SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
par: Gao, Shuzheng, et autres
Publié: (2025)

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code
par: Zhang, Kechi, et autres
Publié: (2024)

Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation
par: Li, Tian, et autres
Publié: (2025)

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
par: Yang, Guang, et autres
Publié: (2024)

VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
par: Le, Cuong Chi, et autres
Publié: (2024)

CasModaTest: A Cascaded and Model-agnostic Self-directed Framework for Unit Test Generation
par: Ni, Chao, et autres
Publié: (2024)

SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking
par: Ma, Hongru, et autres
Publié: (2025)

LaTCoder: Converting Webpage Design to Code with Layout-as-Thought
par: Gui, Yi, et autres
Publié: (2025)

Uncovering Weaknesses in Neural Code Generation
par: Lian, Xiaoli, et autres
Publié: (2024)

FDI: Attack Neural Code Generation Systems through User Feedback Channel
par: Sun, Zhensu, et autres
Publié: (2024)

Fixing Large Language Models' Specification Misunderstanding for Better Code Generation
par: Tian, Zhao, et autres
Publié: (2023)

A Multi-agent Onboarding Assistant based on Large Language Models, Retrieval Augmented Generation, and Chain-of-Thought
par: Ionescu, Andrei Cristian, et autres
Publié: (2025)

Aligning Requirement for Large Language Model's Code Generation
par: Tian, Zhao, et autres
Publié: (2025)

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
par: Li, Yue, et autres
Publié: (2026)

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
par: Zhang, Kechi, et autres
Publié: (2024)

ReVul-CoT: Towards Effective Software Vulnerability Assessment with Retrieval-Augmented Generation and Chain-of-Thought Prompting
par: Chen, Zhijie, et autres
Publié: (2025)

Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks
par: Mohseni, Seyedreza, et autres
Publié: (2026)

Leveraging Code Cohesion Analysis to Identify Source Code Supply Chain Attacks
par: Reuben, Maor, et autres
Publié: (2025)

CodeScore: Evaluating Code Generation by Learning Code Execution
par: Dong, Yihong, et autres
Publié: (2023)

Enhancing Interpretability in Software Change Management with Chain-of-Thought Reasoning
par: Sun, Yongqian, et autres
Publié: (2025)

CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
par: Pan, Ruwei, et autres
Publié: (2025)

RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation
par: Liu, Yang, et autres
Publié: (2025)

Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging
par: Hua, Ziyue, et autres
Publié: (2026)

Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
par: Yang, Guang, et autres
Publié: (2026)

Inducing Vulnerable Code Generation in LLM Coding Assistants
par: Zeng, Binqi, et autres
Publié: (2025)

Adversarial Attack Classification and Robustness Testing for Large Language Models for Code
par: Liu, Yang, et autres
Publié: (2025)

A Survey on Evaluating Large Language Models in Code Generation Tasks
par: Chen, Liguo, et autres
Publié: (2024)

BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks
par: Xiao, Yisong, et autres
Publié: (2024)

Adversarial Attacks on Code Models with Discriminative Graph Patterns
par: Nguyen, Thanh-Dat, et autres
Publié: (2023)

Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
par: Zhang, Wei, et autres
Publié: (2024)

Self-planning Code Generation with Large Language Models
par: Jiang, Xue, et autres
Publié: (2023)

Backdoors in Code Summarizers: How Bad Is It?
par: Wang, Chenyu, et autres
Publié: (2025)

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision
par: Lu, Xu, et autres
Publié: (2025)