# Signal Watermark on Large Language Models

arXiv: https://arxiv.org/abs/2410.06545 · HTML: https://mlsanity.com/paper/2410.06545/

## 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 19 of its 31 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## 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, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding](https://mlsanity.com/paper/2009.03015/) (2020)
- [Protecting Language Generation Models via Invisible Watermarking](https://mlsanity.com/paper/2302.03162/) (2023)
- [Robust Multi-bit Natural Language Watermarking through Invariant Features](https://mlsanity.com/paper/2305.01904/) (2023)
- [CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks](https://mlsanity.com/paper/2209.08773/) (2022)
- [Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark](https://mlsanity.com/paper/2305.10036/) (2023)
- [Distillation-Resistant Watermarking for Model Protection in NLP](https://mlsanity.com/paper/2210.03312/) (2022)
- [Watermarking LLMs with Weight Quantization](https://mlsanity.com/paper/2310.11237/) (2023)

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

- [Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends](https://mlsanity.com/paper/2508.11548/) (2025)

## Abstract (arXiv)

As Large Language Models (LLMs) become increasingly sophisticated, they raise significant security concerns, including the creation of fake news and academic misuse. Most detectors for identifying model-generated text are limited by their reliance on variance in perplexity and burstiness, and they require substantial computational resources. In this paper, we proposed a watermarking method embedding a specific watermark into the text during its generation by LLMs, based on a pre-defined signal pattern. This technique not only ensures the watermark's invisibility to humans but also maintains the quality and grammatical integrity of model-generated text. We utilize LLMs and Fast Fourier Transform (FFT) for token probability computation and detection of the signal watermark. The unique application of signal processing principles within the realm of text generation by LLMs allows for subtle yet effective embedding of watermarks, which do not compromise the quality or coherence of the generated text. Our method has been empirically validated across multiple LLMs, consistently maintaining high detection accuracy, even with variations in temperature settings during text generation. In the experiment of distinguishing between human-written and watermarked text, our method achieved an AUROC score of 0.97, significantly outperforming existing methods like GPTZero, which scored 0.64. The watermark's resilience to various attacking scenarios further confirms its robustness, addressing significant challenges in model-generated text authentication.