Copertina

Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ouyang, Sheng, Qin, Yihao, Lin, Bo, Chen, Liqian, Mao, Xiaoguang, Wang, Shangwen
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Keep It Simple: Towards Accurate Vulnerability Detection for Large Code Graphs
di: Peng, Xin, et al.
Pubblicazione: (2024)

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

Large Language Models-Aided Program Debloating
di: Lin, Bo, et al.
Pubblicazione: (2025)

There are More Fish in the Sea: Automated Vulnerability Repair via Binary Templates
di: Lin, Bo, et al.
Pubblicazione: (2024)

Fault Localization from the Semantic Code Search Perspective
di: Qin, Yihao, et al.
Pubblicazione: (2024)

AgentFL: Scaling LLM-based Fault Localization to Project-Level Context
di: Qin, Yihao, et al.
Pubblicazione: (2024)

Atomizer: An LLM-based Collaborative Multi-Agent Framework for Intent-Driven Commit Untangling
di: Zhu, Kangchen, et al.
Pubblicazione: (2026)

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

Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
di: Peng, Xin, et al.
Pubblicazione: (2026)

Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks
di: Yang, Kang, et al.
Pubblicazione: (2025)

Debug Like a Human: Scaling LLM-based Fault Localization to Processor Design via Block-Level Instruction-Oriented Slicing
di: Liu, Zizhen, et al.
Pubblicazione: (2026)

Prompt Optimization for LLM Code Generation via Reinforcement Learning
di: Esfahani, Ali Mohammadi, et al.
Pubblicazione: (2026)

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

Assessing the Impact of Requirement Ambiguity on LLM-based Function-Level Code Generation
di: Yang, Di, et al.
Pubblicazione: (2026)

Shapley-Guided Neural Repair Approach via Derivative-Free Optimization
di: Sun, Xinyu, et al.
Pubblicazione: (2026)

Prompt-based Code Completion via Multi-Retrieval Augmented Generation
di: Tan, Hanzhuo, et al.
Pubblicazione: (2024)

SolSearch: An LLM-Driven Framework for Efficient SAT-Solving Code Generation
di: Sheng, Junjie, et al.
Pubblicazione: (2025)

GeoJSON Agents:A Multi-Agent LLM Architecture for Geospatial Analysis-Function Calling vs Code Generation
di: Luo, Qianqian, et al.
Pubblicazione: (2025)

Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
di: Gong, Jingzhi, et al.
Pubblicazione: (2025)

CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs
di: He, Pengfei, et al.
Pubblicazione: (2025)

Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering
di: Zhang, Tanghaoran, et al.
Pubblicazione: (2024)

When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
di: AKLI, Amal, et al.
Pubblicazione: (2026)

Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation
di: Zhang, Binquan, et al.
Pubblicazione: (2025)

Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation
di: Ye, Sixiang, et al.
Pubblicazione: (2025)

BitsAI-CR: Automated Code Review via LLM in Practice
di: Sun, Tao, et al.
Pubblicazione: (2025)

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

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

R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability
di: Wang, Yifei, et al.
Pubblicazione: (2026)

Code Roulette: How Prompt Variability Affects LLM Code Generation
di: Paleyes, Andrei, et al.
Pubblicazione: (2025)

Bias Unveiled: Investigating Social Bias in LLM-Generated Code
di: Ling, Lin, et al.
Pubblicazione: (2024)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
di: Zhao, Jian, et al.
Pubblicazione: (2024)

Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks
di: Zhou, Shide, et al.
Pubblicazione: (2024)

Chart2Code-MoLA: Efficient Multi-Modal Code Generation via Adaptive Expert Routing
di: Wang, Yifei, et al.
Pubblicazione: (2025)

Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
di: Ji, Kexing, et al.
Pubblicazione: (2025)

HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization
di: Jiang, Hanyun, et al.
Pubblicazione: (2026)

When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
di: Sun, Zhensu, et al.
Pubblicazione: (2024)

An Empirical Study of the Non-determinism of ChatGPT in Code Generation
di: Ouyang, Shuyin, et al.
Pubblicazione: (2023)

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation
di: Dai, Yihan, et al.
Pubblicazione: (2025)

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
di: Sun, Zhensu, et al.
Pubblicazione: (2022)