# LLM Watermarking Using Mixtures and Statistical-to-Computational Gaps

arXiv: https://arxiv.org/abs/2505.01484 · HTML: https://mlsanity.com/paper/2505.01484/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 2 May 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, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding](https://mlsanity.com/paper/2009.03015/) (2020)
- [Notes on Computational Hardness of Hypothesis Testing: Predictions using the Low-Degree Likelihood Ratio](https://mlsanity.com/paper/1907.11636/) (2019)
- [A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules](https://mlsanity.com/paper/2404.01245/) (2024)
- [Reducibility and Statistical-Computational Gaps from Secret Leakage](https://mlsanity.com/paper/2005.08099/) (2020)
- [Provably Robust Watermarks for Open-Source Language Models](https://mlsanity.com/paper/2410.18861/) (2024)
- [GaussMark: A Practical Approach for Structural Watermarking of Language Models](https://mlsanity.com/paper/2501.13941/) (2025)

## Built on by (most cited first, 1 of 1)

- [Watermark Forensics for Generative Models: An Information-Theoretic Perspective](https://mlsanity.com/paper/2607.13003/) (2026)

## Abstract (arXiv)

Given a text, can we determine whether it was generated by a large language model (LLM) or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed setting. Also, in the harder open setting, where the adversary has access to most of the model, we propose an unremovable watermarking scheme.