# MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?

arXiv: https://arxiv.org/abs/2507.19598 · HTML: https://mlsanity.com/paper/2507.19598/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 67 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 30 of 43)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion](https://mlsanity.com/paper/2007.02220/) (2020)
- [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)
- [Natural Attack for Pre-trained Models of Code](https://mlsanity.com/paper/2201.08698/) (2022)
- [Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition](https://mlsanity.com/paper/2311.16119/) (2023)
- [XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence](https://mlsanity.com/paper/2206.08474/) (2022)
- [CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models](https://mlsanity.com/paper/2206.00052/) (2022)
- [Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs](https://mlsanity.com/paper/2402.14872/) (2024)
- [Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs](https://mlsanity.com/paper/2406.09324/) (2024)
- [CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference](https://mlsanity.com/paper/2406.17626/) (2024)
- [When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search](https://mlsanity.com/paper/2406.08705/) (2024)

## Built on by (most cited first, 7 of 7)

- [When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?](https://mlsanity.com/paper/2510.17862/) (2025)
- [MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents](https://mlsanity.com/paper/2605.03952/) (2026)
- [Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)](https://mlsanity.com/paper/2605.20351/) (2026)
- [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)
- [Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats](https://mlsanity.com/paper/2606.26377/) (2026)
- [CS-Guard: Benchmarking LLM Guardrails for Code Generation Security](https://mlsanity.com/paper/2609.09798/) (2026)

## Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have significantly enhanced their code generation capabilities. However, their robustness against adversarial misuse, particularly through multi-turn malicious coding prompts, remains underexplored. In this work, we introduce code decomposition attacks, where a malicious coding task is broken down into a series of seemingly benign subtasks across multiple conversational turns to evade safety filters. To facilitate systematic evaluation, we introduce benchmarkname, a large-scale benchmark designed to evaluate the robustness of code LLMs against both single-turn and multi-turn malicious prompts. Empirical results across open- and closed-source models reveal persistent vulnerabilities, especially under multi-turn scenarios. Fine-tuning on MOCHA improves rejection rates while preserving coding ability, and importantly, enhances robustness on external adversarial datasets with up to 32.4% increase in rejection rates without any additional supervision.