Search papers, labs, and topics across Lattice.
3
0
6
37
SpreadMark's innovative dense pseudo-random codeword embedding makes watermarking significantly more resilient to attacks, outperforming traditional methods in both robustness and imperceptibility.
A watermark can not only identify machine-generated text but also attribute it to specific users and extract hidden information, all governed by a precise information-theoretic framework.
Watermarking LLM-agent trajectories just got a major upgrade鈥擳RACE achieves near-perfect detection without sacrificing performance, even under aggressive adversarial conditions.
