Conference
Open access
2026
RShield: A User-level Traceable Backdoor Watermark for LLMs in Embedding-as-a-Service
RShield is proposed, a multi-bit backdoor watermarking that enables reliable user-level attri-bution of LLMs for EaaS under model extraction attacks, and achieves 100% multi-bit watermark recovery and high semantic fidelity under model extraction attacks compared to existing methods.
Lin Xiang, Yufan Zhong, Chengfu Ou et al.
· Annual Meeting of the Associ... · 0 citations