TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy

Reported by arXiv cs.CR (Ruibo Chen, Zhengmian Hu, Donghang Lu, Xuehao Cui, Georgios Milis, Yihan Wu, Jian Du, Heng Huang)

Summary by Cyber Security News30 Sep 2026, 06:00 CEST

About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2609.36372

arXiv:2609.36372v1 Announce Type: new Abstract: Distortion-free watermarking enables reliable attribution of machine-generated text while preserving output distribution. However, existing methods operate independently on each generated token, making their detection capability fundamentally constrained by the entropy of the next-token distribution.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning

Hackers exploit Citrix NetScaler zero-day to deploy web shells

NetScaler zero-day exploitation escalates into mass attacks (CVE-2026-88771)

OpenAI benches GPT-6.1 Astra for overstepping the mark

CVE-2026-82804: Apache DolphinScheduler: Command Injection in the Alert Script Plugin

Scans for Wordfence Protected Websites, (Tue, Sep 29th)