AI watermarking detection relies on original logits and prompts

binarybits · x · 2026-08-16

A technical discussion on the feasibility of AI watermarking detection: Is access to the logits from the original generation required? Without the full original prompt, how does one identify which words to inspect for the watermark? It highlights the difficulty of detection without original logits.

Related event: Debating AI Text Watermark Detection: Logits Dependence vs Hash-Based Frequency Checks(4 posts)→

Original post →

More from Safety

Safety channel →