Is Watermarking LLM-Generated Code Robust?
Tarun Suresh
2024 poster
in
Affinity Event: Tiny Papers Poster Session 1
in
Affinity Event: Tiny Papers Poster Session 1
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.
Chat is not available.
Successful Page Load