An RL-trained policy adaptively biases token choices to watermark LLM-generated code while preserving executable behavior.
A survey of static software watermarking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimizing Token Choice for Code Watermarking: An RL Approach
An RL-trained policy adaptively biases token choices to watermark LLM-generated code while preserving executable behavior.