Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings Paper • 2606.31602 • Published Sep 4
LLM Self-Recognition: Steering and Retrieving Activation Signatures Paper • 2606.06315 • Published Jun 4
view article Article Highlights from the First ICLR 2025 Watermarking Workshop hadyelsahar • May 14, 2025 • 14
⛔️🔦 Provenance, Watermarking & Deepfake Detection Collection Technical tools for more control over synthetic content • 16 items • Updated Dec 19, 2025 • 46
Three Bricks to Consolidate Watermarks for Large Language Models Paper • 2308.00113 • Published Jul 26, 2023 • 15