// NATURE NEWS — SPAZIO & SCIENZA
AI watermarking efforts must encourage independent public scrutiny
Search author on:
PubMed
Google Scholar
Nanjing Normal University of Special Education, Nanjing, China.
Search author on:
PubMed
Google Scholar
Your News story on Anthropic’s invisible watermarks highlights their potential as transparency signals for text generated with the help of artificial intelligence and their limits as evidence of misconduct (see Nature https://doi.org/rskt; 2026). But such watermarks can become targets for attack, too. In tests of previous efforts, attackers inferred patterns through model queries and then spoofed or removed the watermarks for less than US$50, with a success rate of roughly 80% (N. Jovanović et al. Proc. 41st Int. Conf. Mach. Learn. 235, 22570–22593; 2024).
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
Prices may be subject to local taxes which are calculated during checkout
Nature’s job-satisfaction survey highlights the changing geography of science
Is AI eroding PhD students’ critical thinking and analysis skills?
China’s AI research is booming: what it’s like to be on the front line