AI RESEARCH
The Forensic Cost of Watermark Removal
arXiv CS.CV
•
ArXi:2604.25491v1 Announce Type: new Current watermark removal methods are evaluated on two axes: attack success rate and perceptual quality. We show this is insufficient. While state-of-the-art attacks successfully degrade the watermark signal without visible distortion, they leave distinct statistical artifacts that betray the removal attempt. We name this overlooked axis Watermark Removal Detection (WRD) and nstrate that a modern classifier trained on these artifacts achieves state-of-the-art detection rates at $10^{-3}$ FPR across every removal method tested.