In recent years, homomorphic encryption (HE) schemes based on the Ring Learning with Errors (RLWE) problem have rapidly developed and been widely applied to secure computation tasks, including privacy-preserving deep learning inference, privacy-preserving database queries, and related applications. However, most existing HE schemes focus primarily on the feasibility and efficiency of homomorphic computation, often neglecting practical requirements such as copyright protection of ciphertexts, source authentication, and supervision during computation. To address these issues, we propose a watermarking technique for RLWE-based HE ciphertexts. The algebraic structure of RLWE polynomials allows us to embed small noise as watermarking information into the ciphertext polynomials without affecting the plaintext values. However, HE ciphertexts typically undergo multiple homomorphic operations, which can distort or even remove the embedded watermark information. To address this challenge, we propose two practical solutions. The first, ARWMark, is a watermarking scheme based on noise stratification and is robust to homomorphic additive operations. The second scheme, MRWMark, is constructed using the roots of a linear equation and is resilient to both homomorphic additive and multiplicative operations, while supporting zero-bit watermarking. We provide a detailed theoretical analysis, proving that our schemes do not compromise the original security of HE, while ensuring the correctness and robustness of the proposed watermarking techniques. Furthermore, we conduct extensive experiments to demonstrate the effectiveness of both watermarking schemes.

翻译：暂无翻译