Verified75% confidenceFactExact time
Invisible watermarking technology embeds statistical signals during the generation phase of large language models by fine-tuning the token sampling strategy (dividing the vocabulary into green and red tokens and biasing toward green tokens).
3
Sources
75%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
How Zhuque AI Detection Works: A Guide for Content Creators on Reducing Traffic Restrictions
bilibili宋哥讲AI图文7/8/2026
Related Claims
VerifiedThe green token watermarking method divides the vocabulary into green and red groups based on the hash value of the previous token before sampling, applies probability weighting to green tokens, and causes the frequency of green tokens in watermarked text to be significantly higher than the natural language baseline82% similarVerifiedText watermarking technology was proposed by Kirchenbauer et al. at the University of Maryland in 2023, embedding hidden signals by dividing the vocabulary into green and red groups and biasing toward selecting green tokens.77% similarUnverifiedIndustry text watermarking schemes typically introduce specific statistical biases during the model's token generation process, causing the output text to carry patterns that are algorithmically detectable but imperceptible to humans.75% similarUnverifiedThe classic approach to watermarking is to randomly divide the vocabulary into a green list and a red list before sampling, with the division typically determined by a hash function applied to the preceding token.71% similarUnverifiedSimple editing operations such as replacing synonyms, adjusting word order, and inserting or deleting words can also weaken watermarks, and modifying a sufficient proportion of tokens can bring the green-list statistics back to a random level.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/370801API
curl https://kongchang.com/api/v1/knowledge/claims/370801MCP
get_claim(id=370801)