Is Watermarking LLM-Generated Code Robust?
Tarun Suresh
Abstract
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 text, we show that it is easy to remove these watermarks on code by simple semantic-preserving transformations.
Video
Chat is not available.
Successful Page Load