Beyond Dataset Watermarking: Model-Level Copyright Protection for Code Summarization Models

TL;DR

This paper introduces ModMark, a model-level digital watermarking method for code summarization models that enhances copyright protection across multiple programming languages while maintaining concealment and robustness.

Contribution

ModMark is a novel watermarking technique that uses tokenizer fine-tuning for cross-language generalization and code noise injection for concealment, addressing limitations of prior dataset and style-based methods.

Findings

Achieves 100% watermark verification rate across various languages.

Demonstrates robustness against automated detection.

Maintains concealment and effectiveness of watermarks.

Abstract

Code Summarization Model (CSM) has been widely used in code production, such as online and web programming for PHP and Javascript. CSMs are essential tools in code production, enhancing software development efficiency and driving innovation in automated code analysis. However, CSMs face risks of exploitation by unauthorized users, particularly in an online environment where CSMs can be easily shared and disseminated. To address these risks, digital watermarks offer a promising solution by embedding imperceptible signatures within the models to assert copyright ownership and track unauthorized usage. Traditional watermarking for CSM copyright protection faces two main challenges: 1) dataset watermarking methods require separate design of triggers and watermark features based on the characteristics of different programming languages, which not only increases the computation complexity but also leads to a lack of generalization, 2) existing watermarks based on code style transformation are easily identifiable by automated detection, demonstrating poor concealment. To tackle these issues, we propose ModMark , a novel model-level digital watermark embedding method. Specifically, by fine-tuning the tokenizer, ModMark achieves cross-language generalization while reducing the complexity of watermark design. Moreover, we employ code noise injection techniques to effectively prevent trigger detection. Experimental results show that our method can achieve 100% watermark verification rate across various programming languages' CSMs, and the concealment and effectiveness of ModMark can also be guaranteed.