Jonathan Hong Jin Ng
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
The paper analyzes the robustness of current LLM watermarking schemes against various text modifications, concluding that watermarks can be removed with reasonable effort.
Highlighted terms show continued research focus across papers