Existing LLM watermarking schemes can be defeated by semantic-preserving attacks including lexical changes, machine translation, and neural paraphrasing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
Existing LLM watermarking schemes can be defeated by semantic-preserving attacks including lexical changes, machine translation, and neural paraphrasing.