Detecting AI text watermarking via hash-matching frequency

binarybits · x · 2026-08-16

A discussion on an AI watermarking detection method: compute a hash of the preceding 16 words and check if subsequent words meet hash-matching criteria. If the frequency of such matches is implausibly high, it serves as a sign that the text was AI-generated.

Related event: Does AI Watermark Detection Require Original Logits?(4 posts)→

Original post →

More from Safety

Safety channel →