# VOW: Verifiable and Oblivious Watermark Detection for Large Language Models

arXiv: https://arxiv.org/abs/2604.27666 · HTML: https://mlsanity.com/paper/2604.27666/

## 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 21 of its 41 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## 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, 21 of 21)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'](https://mlsanity.com/paper/2410.12954/) (2024)
- [Protecting Language Generation Models via Invisible Watermarking](https://mlsanity.com/paper/2302.03162/) (2023)
- [A Robust Semantics-based Watermark for Large Language Model against Paraphrasing](https://mlsanity.com/paper/2311.08721/) (2023)
- [Publicly-Detectable Watermarking for Language Models](https://mlsanity.com/paper/2310.18491/) (2023)
- [An Unforgeable Publicly Verifiable Watermark for Large Language Models](https://mlsanity.com/paper/2307.16230/) (2023)
- [Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand](https://mlsanity.com/paper/2310.14942/) (2023)
- [Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs](https://mlsanity.com/paper/2504.04715/) (2025)
- [Malla: Demystifying Real-world Large Language Model Integrated Malicious Services](https://mlsanity.com/paper/2401.03315/) (2024)
- [Scaling up Trustless DNN Inference with Zero-Knowledge Proofs](https://mlsanity.com/paper/2210.08674/) (2022)
- [Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges](https://mlsanity.com/paper/2403.18249/) (2024)
- [Auditing Prompt Caching in Language Model APIs](https://mlsanity.com/paper/2502.07776/) (2025)
- [Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge](https://mlsanity.com/paper/2503.04036/) (2025)

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

- [LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematization](https://mlsanity.com/paper/2607.10103/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a centralized trust model. This model forces users to reveal potentially sensitive text to a provider for detection and offers no way to verify the integrity of the result. While asymmetric schemes have been proposed to address these issues, they are either impractical for short texts or lack formal guarantees linking watermark insertion and detection. We propose VOW, a new protocol that achieves both privacy-preserving and cryptographically verifiable watermark detection with high efficiency. Our approach formulates detection as a secure two-party computation problem, instantiating the watermark's core logic with a Verifiable Oblivious Pseudorandom Function (VOPRF). This allows the user and provider to perform detection without the user's text being revealed, while the provider's result is verifiable. Our comprehensive evaluation shows that VOW is practical for short texts and provides a crucial reassessment of watermark robustness against modern paraphrasing attacks.