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

arXiv: https://arxiv.org/abs/2503.17953 · HTML: https://mlsanity.com/paper/2503.17953/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 23 Mar 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction](https://mlsanity.com/paper/2402.18104/) (2024)
- [RedCode: Risky Code Execution and Generation Benchmark for Code Agents](https://mlsanity.com/paper/2411.07781/) (2024)
- [CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion](https://mlsanity.com/paper/2403.07865/) (2024)
- [Intention Analysis Makes LLMs A Good Jailbreak Defender](https://mlsanity.com/paper/2401.06561/) (2024)
- [Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning](https://mlsanity.com/paper/2304.11384/) (2023)
- [Towards an Understanding of Large Language Models in Software Engineering Tasks](https://mlsanity.com/paper/2308.11396/) (2023)
- [CodeDPO: Aligning Code Models with Self Generated and Verified Source Code](https://mlsanity.com/paper/2410.05605/) (2024)
- [RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code](https://mlsanity.com/paper/2409.15154/) (2024)
- [CCT5: A Code-Change-Oriented Pre-Trained Model](https://mlsanity.com/paper/2305.10785/) (2023)

## Built on by (most cited first, 5 of 5)

- [MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?](https://mlsanity.com/paper/2507.19598/) (2025)
- [Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code](https://mlsanity.com/paper/2606.11817/) (2026)
- [CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts](https://mlsanity.com/paper/2606.19235/) (2026)
- [Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents](https://mlsanity.com/paper/2607.03968/) (2026)
- [CS-Guard: Benchmarking LLM Guardrails for Code Generation Security](https://mlsanity.com/paper/2609.09798/) (2026)

## Abstract (arXiv)

The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development efficiency and productivity. Notably, LLMs like GPT-4 have demonstrated remarkable proficiency in text-to-code generation tasks. However, the growing reliance on LLMs for code generation necessitates a critical examination of the safety implications associated with their outputs. Existing research efforts have primarily focused on verifying the functional correctness of LLMs, overlooking their safety in code generation. This paper introduces a jailbreaking approach, CodeJailbreaker, designed to uncover safety concerns in LLM-based code generation. The basic observation is that existing safety mechanisms for LLMs are built through the instruction-following paradigm, where malicious intent is explicitly articulated within the instruction of the prompt. Consequently, CodeJailbreaker explores to construct a prompt whose instruction is benign and the malicious intent is implicitly encoded in a covert channel, i.e., the commit message, to bypass the safety mechanism. Experiments on the recently-released RMCBench benchmark demonstrate that CodeJailbreaker markedly surpasses the conventional jailbreaking strategy, which explicitly conveys malicious intents in the instructions, in terms of the attack effectiveness across three code generation tasks. This study challenges the traditional safety paradigms in LLM-based code generation, emphasizing the need for enhanced safety measures in safeguarding against implicit malicious cues.