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.
No takes yet. Share an insight, caveat, or question.
Suresh et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: