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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wahed, Muntasir, Zhou, Xiaona, Nguyen, Kiet A., Yu, Tianjiao, Diwan, Nirav, Wang, Gang, Hakkani-Tür, Dilek, Lourentzou, Ismini
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911078156337152
author Wahed, Muntasir
Zhou, Xiaona
Nguyen, Kiet A.
Yu, Tianjiao
Diwan, Nirav
Wang, Gang
Hakkani-Tür, Dilek
Lourentzou, Ismini
author_facet Wahed, Muntasir
Zhou, Xiaona
Nguyen, Kiet A.
Yu, Tianjiao
Diwan, Nirav
Wang, Gang
Hakkani-Tür, Dilek
Lourentzou, Ismini
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19598
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
Wahed, Muntasir
Zhou, Xiaona
Nguyen, Kiet A.
Yu, Tianjiao
Diwan, Nirav
Wang, Gang
Hakkani-Tür, Dilek
Lourentzou, Ismini
Computation and Language
Artificial Intelligence
Cryptography and Security
Machine Learning
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.
title MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
topic Computation and Language
Artificial Intelligence
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2507.19598