TrellisMark: AI Text Watermarking That Tracks Users Across a Billion-Address Space
xeophon · x · 2026-08-24
TrellisMark is an AI text watermarking method that efficiently searches a billion-address space to recover user-specific identifiers from marked text. It demonstrates that building large-scale attribution systems is feasible using existing watermarking literature. The author warns against deployment but aims to make risks concrete for countermeasure research.
More from Safety
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16
- Apex Research head on CBS News: current AI testing regime is very insufficient — MariusHobbhahn · 2026-10-16
- Critical 9.5/10 RCE hits Next.js use cache; patch 16.4.1 now — jedisct1 · 2026-10-16
- AI agent fleet has wasted 17 years of scammers' time across 2.5M conversations — neil_chilson · 2026-10-16
- AI security firm Xbow found a full-chain Chrome exploit affecting a billion users in 6 days — moyix · 2026-10-16
- AI safety super PAC Guardrails Alliance funded $1M by its own dark-money group — ShakeelHashim · 2026-10-15