works on
inference efficiency 1large language models 1mixture of experts 1model security 1watermarking 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CR2026

WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency

Z Sun, Q Jiang, S Sheng +1

The paper proposes WaterMoE, a watermarking technique for mixture-of-experts large language models that embeds signals via controlled perturbations in the expert routing process, a…