# Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding

arXiv: https://arxiv.org/abs/2009.03015 · HTML: https://mlsanity.com/paper/2009.03015/

## Key facts

- Cited by 130 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2020.

## Built on by (most cited first, 30 of 130)

- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [A Semantic Invariant Robust Watermark for Large Language Models](https://mlsanity.com/paper/2310.06356/) (2023)
- [A Survey of Text Watermarking in the Era of Large Language Models](https://mlsanity.com/paper/2312.07913/) (2023)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [Watermark Stealing in Large Language Models](https://mlsanity.com/paper/2402.19361/) (2024)
- [Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection](https://mlsanity.com/paper/2210.00875/) (2022)
- [Robust Multi-bit Natural Language Watermarking through Invariant Features](https://mlsanity.com/paper/2305.01904/) (2023)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [Evading Watermark based Detection of AI-Generated Content](https://mlsanity.com/paper/2305.03807/) (2023)
- [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)
- [Publicly-Detectable Watermarking for Language Models](https://mlsanity.com/paper/2310.18491/) (2023)
- [A Survey on Detection of LLMs-Generated Content](https://mlsanity.com/paper/2310.15654/) (2023)
- [Adaptive Text Watermark for Large Language Models](https://mlsanity.com/paper/2401.13927/) (2024)
- [Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems](https://mlsanity.com/paper/2401.05778/) (2024)
- [An Unforgeable Publicly Verifiable Watermark for Large Language Models](https://mlsanity.com/paper/2307.16230/) (2023)
- [Advancing Beyond Identification: Multi-bit Watermark for Large Language Models](https://mlsanity.com/paper/2308.00221/) (2023)
- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models](https://mlsanity.com/paper/2310.07710/) (2023)
- [Towards Codable Watermarking for Injecting Multi-bits Information to LLMs](https://mlsanity.com/paper/2307.15992/) (2023)
- [Changing the World by Changing the Data](https://mlsanity.com/paper/2105.13947/) (2021)

## Abstract (arXiv)

Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential misuse of such models for malicious purposes. In this paper, we study natural language watermarking as a defense to help better mark and trace the provenance of text. We introduce the Adversarial Watermarking Transformer (AWT) with a jointly trained encoder-decoder and adversarial training that, given an input text and a binary message, generates an output text that is unobtrusively encoded with the given message. We further study different training and inference strategies to achieve minimal changes to the semantics and correctness of the input text. AWT is the first end-to-end model to hide data in text by automatically learning -- without ground truth -- word substitutions along with their locations in order to encode the message. We empirically show that our model is effective in largely preserving text utility and decoding the watermark while hiding its presence against adversaries. Additionally, we demonstrate that our method is robust against a range of attacks.