SOURCE-LINKED INTELLIGENCE

Semantic Watermarking with Order-Robust Detection over Sub-sentence Units

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Semantic watermarks tie the mark to sentence meaning rather than token choices, promising robustness to content-preserving edits. However, the detector only observes attacker-supplied text, which can be reworded, reordered, or resegmented to evade detection without content loss. Rewording, reordering, and resegmentation all cause embedding displacement: detection tests embeddings different from those selected during watermarking and can therefore lose the mark. Our adaptive embedding displacement attack (EDA) admits all three edits under a single objective that maximizes this displacement. It

Read original source ↗ Open in workspace

recordType

paper

region

Global