# WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance

arXiv: https://arxiv.org/abs/2608.29151 · HTML: https://mlsanity.com/paper/2608.29151/

## 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 32 of its 43 references that are in the map.
- First posted on arXiv 29 Aug 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, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2512.20848/) (2025)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [Watermarking Makes Language Models Radioactive](https://mlsanity.com/paper/2402.14904/) (2024)
- [Revisiting the Robustness of Watermarking to Paraphrasing Attacks](https://mlsanity.com/paper/2411.05277/) (2024)
- [Watermarking LLMs with Weight Quantization](https://mlsanity.com/paper/2310.11237/) (2023)
- [Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach](https://mlsanity.com/paper/2410.02890/) (2024)
- [GaussMark: A Practical Approach for Structural Watermarking of Language Models](https://mlsanity.com/paper/2501.13941/) (2025)
- [Towards Watermarking of Open-Source LLMs](https://mlsanity.com/paper/2502.10525/) (2025)
- [Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation](https://mlsanity.com/paper/2504.17480/) (2025)
- [GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs](https://mlsanity.com/paper/2512.21008/) (2025)

## Abstract (arXiv)

Large Language Model (LLM) watermarks provide a mechanism for text provenance, enabling model owners to identify machine-generated content and attribute it to a specific watermarked model. However, current LLM watermarking approaches predominantly rely on inference-time sampler methods and focus their analysis on dense models. Inference-time methods are only effective when the text is explicitly generated via the model owner's controlled API; they fail in a post-compromise scenario. An adversary who steals or leaks the model weights gains complete control over inference and can simply run an unmodified sampler, bypassing the watermark and preventing post-theft attribution. In this work, we introduce Watermarking of Experts (WoE), a novel black-box text provenance method that leverages the unique structural properties of sparse Mixture-of-Experts (MoE) models. WoE biases the vocabulary of specific experts and shifts the watermark signal embedding away from unenforceable inference wrappers. This approach ensures the watermark remains intrinsic to the model parameters, enabling defenders to attribute text generated by stolen weights, leaked checkpoints, and secondary dense models distilled from the stolen architecture without needing access to the adversary's deployment or weights. We evaluate WoE across eight MoE models, demonstrating successful watermark detection from suspect text, achieving an average true positive rate of 90.1% at a 1% false positive rate, reaching up to 94.9%, while largely preserving general model utility. Furthermore, WoE remains detectable under adversarial supervised fine-tuning, model extraction, and output-level paraphrasing, forcing malicious actors into a trade-off in which weakening the attribution signal requires additional model adaptation or text-rewriting operations, or compromises the utility of the resulting output.