We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models. Although existing works showed that watermarking can be robust for natural language, we show that it is easy to remove these watermarks on code by semantic-preserving transformations.

翻译：本研究首次探讨了现有水印技术在大语言模型生成的Python代码上的稳健性。尽管已有研究表明水印技术对自然语言具有稳健性，但我们发现通过语义保持的代码转换可以轻易移除这些水印。