# CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants

arXiv: https://arxiv.org/abs/2404.09066 · HTML: https://mlsanity.com/paper/2404.09066/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants](https://mlsanity.com/paper/2208.09727/) (2022)
- [How Secure is Code Generated by ChatGPT?](https://mlsanity.com/paper/2304.09655/) (2023)
- [TEMPERA: Test-Time Prompting via Reinforcement Learning](https://mlsanity.com/paper/2211.11890/) (2022)
- [CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning](https://mlsanity.com/paper/2110.12925/) (2021)
- [PRewrite: Prompt Rewriting with Reinforcement Learning](https://mlsanity.com/paper/2401.08189/) (2024)
- [Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study](https://mlsanity.com/paper/2309.08221/) (2023)
- [RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions](https://mlsanity.com/paper/2302.09466/) (2023)
- [Automatic Code Documentation Generation Using GPT-3](https://mlsanity.com/paper/2209.02235/) (2022)
- [Automatic Code Summarization via ChatGPT: How Far Are We?](https://mlsanity.com/paper/2305.12865/) (2023)
- [Analysis of ChatGPT on Source Code](https://mlsanity.com/paper/2306.00597/) (2023)
- [Using ChatGPT as a Static Application Security Testing Tool](https://mlsanity.com/paper/2308.14434/) (2023)

## Built on by (most cited first, 3 of 3)

- [Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs](https://mlsanity.com/paper/2406.20098/) (2024)
- [VeriLeaky: Navigating IP Protection vs Utility in Fine-Tuning for LLM-Driven Verilog Coding](https://mlsanity.com/paper/2503.13116/) (2025)
- [Effective Code Membership Inference for Code Completion Models via Adversarial Prompts](https://mlsanity.com/paper/2511.15107/) (2025)

## Abstract (arXiv)

LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time suggestions based on the developer's codebase. While beneficial, the use of these tools can inadvertently expose the developer's proprietary code to the code assistant service provider during the development process. In this work, we propose a method to mitigate the risk of code leakage when using LLM-based code assistants. CodeCloak is a novel deep reinforcement learning agent that manipulates the prompts before sending them to the code assistant service. CodeCloak aims to achieve the following two contradictory goals: (i) minimizing code leakage, while (ii) preserving relevant and useful suggestions for the developer. Our evaluation, employing StarCoder and Code Llama, LLM-based code assistants models, demonstrates CodeCloak's effectiveness on a diverse set of code repositories of varying sizes, as well as its transferability across different models. We also designed a method for reconstructing the developer's original codebase from code segments sent to the code assistant service (i.e., prompts) during the development process, to thoroughly analyze code leakage risks and evaluate the effectiveness of CodeCloak under practical development scenarios.