← Search

Connor Choi

1 accepted papers

2025

Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking

ACL 2025long

Watermarking AI-generated text is critical for combating misuse. Yet recent theoretical work argues that any watermark can be erased via random walk attacks that perturb text while preserving quality. However, such attacks rely on two key assumptions: (1) rapid mixing (watermarks dissolve quickly un…