Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
Code watermarking identifies AI-generated code by embedding patterns into the code during generation. Effective watermarking requires meeting two key conditions: the watermark should be reliably detectable, and the code should retain its original functionality. However, existing methods often modify tokens that are critical for program logic, such as keywords in conditional expressions or operators in arithmetic computations. These modifications can cause syntax errors or functional failures, limiting the practical use of watermarking. We present STONE, a method that preserves functional integrity by selectively inserting watermarks only into non-syntax tokens. By excluding tokens essential for code execution, STONE minimizes the risk of functional degradation. In addition, we introduce CWEM, a comprehensive evaluation metric that evaluates watermarking techniques based on correctness, detectability, and naturalness. While correctness and detectability have been widely used, naturalness remains underexplored despite its importance. Unnatural patterns can reveal the presence of a watermark, making it easier for adversaries to remove. We evaluate STONE using CWEM and compare its performance with the state-of-the-art approach. The results show that STONE achieves an average improvement of 7.69% in CWEM across Python, C++, and Java. Our code is available in https://github.com/inistory/STONE-watermarking/.
Code (1)
Similar Papers 제목 키워드 기반
SWaRL: Safeguard Code Watermarking via Reinforcement Learning
We present SWaRL, a robust and fidelity-preserving watermarking framework designed to protect the intellectual property of code LLMs by embedding unique and verifiable signatures in the generated program. Existing waterm…
Reinforcement LearningWaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of…
Breaking Distortion-free Watermarks in Large Language Models
In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM wate…
Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
Most image watermarking systems focus on robustness, capacity, and imperceptibility while treating the embedded payload as meaningless bits. This bit-centric view imposes a hard ceiling on capacity and prevents watermark…
Semantic CommunicationDeepEclipse: How to Break White-Box DNN-Watermarking Schemes
Deep Learning (DL) models have become crucial in digital transformation, thus raising concerns about their intellectual property rights. Different watermarking techniques have been developed to protect Deep Neural Networ…