# PRIVMARK: Private Large Language Models Watermarking with MPC

arXiv: https://arxiv.org/abs/2509.24624 · HTML: https://mlsanity.com/paper/2509.24624/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding](https://mlsanity.com/paper/2009.03015/) (2020)
- [MarkLLM: An Open-Source Toolkit for LLM Watermarking](https://mlsanity.com/paper/2405.10051/) (2024)
- [REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models](https://mlsanity.com/paper/2310.12362/) (2023)
- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [MPCFormer: fast, performant and private Transformer inference with MPC](https://mlsanity.com/paper/2211.01452/) (2022)
- [PUMA: Secure Inference of LLaMA-7B in Five Minutes](https://mlsanity.com/paper/2307.12533/) (2023)
- [Embarrassingly Simple Text Watermarks](https://mlsanity.com/paper/2310.08920/) (2023)
- [PostMark: A Robust Blackbox Watermark for Large Language Models](https://mlsanity.com/paper/2406.14517/) (2024)
- [DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text](https://mlsanity.com/paper/2305.05773/) (2023)
- [Watermarking Techniques for Large Language Models: A Survey](https://mlsanity.com/paper/2409.00089/) (2024)

## Abstract (arXiv)

The rapid growth of Large Language Models (LLMs) has highlighted the pressing need for reliable mechanisms to verify content ownership and ensure traceability. Watermarking offers a promising path forward, but it remains limited by privacy concerns in sensitive scenarios, as traditional approaches often require direct access to a model's parameters or its training data. In this work, we propose a secure multi-party computation (MPC)-based private LLMs watermarking framework, PRIVMARK, to address the concerns. Concretely, we investigate PostMark (EMNLP'2024), one of the state-of-the-art LLMs Watermarking methods, and formulate its basic operations. Then, we construct efficient protocols for these operations using the MPC primitives in a black-box manner. In this way, PRIVMARK enables multiple parties to collaboratively watermark an LLM's output without exposing the model's weights to any single computing party. We implement PRIVMARK using SecretFlow-SPU (USENIX ATC'2023) and evaluate its performance using the ABY3 (CCS'2018) backend. The experimental results show that PRIVMARK achieves semantically identical results compared to the plaintext baseline without MPC and is resistant against paraphrasing and removing attacks with reasonable efficiency.