How to Watermark the RLWE Homomorphic Ciphertexts

• URL: http://arxiv.org/abs/2607.25222v1
• Date: Tue, 28 Jul 2026 02:53:30 GMT
• Title: How to Watermark the RLWE Homomorphic Ciphertexts
• Abstract summary: homomorphic encryption (HE) schemes based on the Ring Learning with Errors problem have rapidly developed.<n>Most existing HE schemes focus primarily on the feasibility and efficiency of homomorphic computation.<n>We propose a watermarking technique for RLWE ciphertexts.
• Score: 1.342943588774946
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Synchronization-Free Algebraic Fingerprints for Large Language Models: From Autoregressive to Diffusion Models [1.1213359816349566]
  Large Language Models (LLMs) have created an urgent need for reliable watermarking methods.<n>We propose a novel synchronization-free watermarking scheme in which every congruence consists of a single binary generated from a pair of neighbouring tokens.
  arXiv  Detail & Related papers  (2026-07-18T05:43:22Z)
• Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings [2.992414059774663]
  This work presents a semantic watermarking scheme for large language models (LLMs)<n> Dual-Embedding Watermarking (DEW) uses contextual and token-level embeddings to enhance robustness against paraphrasing and translation.
  arXiv  Detail & Related papers  (2026-06-30T12:51:30Z)
• Complex Domain Approach for Reversible Data Hiding and Homomorphic Encryption: General Framework and Application to Dispersed Data [0.0]
  This paper introduces Hiding in the Imaginary Domain with Data Encryption (H[i]dden), a novel framework based on complex number arithmetic for simultaneous information embedding and encryption.<n>The paper further introduces two protocols: H[i]dden-EG, for joint reversible data hiding and encryption, and H[i]dden-AggP, for privacy-preserving aggregation of watermarked data, based on partially homomorphic encryption.
  arXiv  Detail & Related papers  (2025-10-04T10:39:48Z)
• Character-Level Perturbations Disrupt LLM Watermarks [64.60090923837701]
  We formalize the system model for Large Language Model (LLM) watermarking.<n>We characterize two realistic threat models constrained on limited access to the watermark detector.<n>We demonstrate character-level perturbations are significantly more effective for watermark removal under the most restrictive threat model.<n> Experiments confirm the superiority of character-level perturbations and the effectiveness of the Genetic Algorithm (GA) in removing watermarks under realistic constraints.
  arXiv  Detail & Related papers  (2025-09-11T02:50:07Z)
• Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models [16.57738116313139]
  We revisit the cryptographic primitives for semantic watermarking.<n>We introduce a novel, general proof of lossless performance based on IND$-CPA security for semantic watermarks.
  arXiv  Detail & Related papers  (2025-03-14T13:45:46Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• Cryptanalysis via Machine Learning Based Information Theoretic Metrics [58.96805474751668]
  We propose two novel applications of machine learning (ML) algorithms to perform cryptanalysis on any cryptosystem.<n>These algorithms can be readily applied in an audit setting to evaluate the robustness of a cryptosystem.<n>We show that our classification model correctly identifies the encryption schemes that are not IND-CPA secure, such as DES, RSA, and AES ECB, with high accuracy.
  arXiv  Detail & Related papers  (2025-01-25T04:53:36Z)
• Encrypted system identification as-a-service via reliable encrypted matrix inversion [0.0]
  Encrypted computation opens up promising avenues across a plethora of application domains. In particular, Arithmetic homomorphic encryption is a natural fit for cloud-based computational services. This paper presents an encrypted system identification service enabled by a reliable encrypted solution to at least squares problems.
  arXiv  Detail & Related papers  (2024-10-27T20:00:04Z)
• WatME: Towards Lossless Watermarking Through Lexical Redundancy [58.61972059246715]
  This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. We introduce Watermarking with Mutual Exclusion (WatME) to seamlessly integrate watermarks.
  arXiv  Detail & Related papers  (2023-11-16T11:58:31Z)
• SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation [72.10931780019297]
  Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. We propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive hashing (LSH) Experimental results show that our novel semantic watermark algorithm is not only more robust than the previous state-of-the-art method on both common and bigram paraphrase attacks, but also is better at preserving the quality of generation.
  arXiv  Detail & Related papers  (2023-10-06T03:33:42Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.