# Can Watermarking Techniques Help Prevent LLM Model Stealing?

arXiv: https://arxiv.org/abs/2607.10794 · HTML: https://mlsanity.com/paper/2607.10794/

## 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 22 of its 38 references that are in the map.
- First posted on arXiv 12 Jul 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, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [High Accuracy and High Fidelity Extraction of Neural Networks](https://mlsanity.com/paper/1909.01838/) (2019)
- [Stealing Part of a Production Language Model](https://mlsanity.com/paper/2403.06634/) (2024)
- [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)
- [Model Reconstruction from Model Explanations](https://mlsanity.com/paper/1807.05185/) (2018)
- [Reverse-Engineering Deep ReLU Networks](https://mlsanity.com/paper/1910.00744/) (2019)
- [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)
- [Cryptanalytic Extraction of Neural Network Models](https://mlsanity.com/paper/2003.04884/) (2020)
- [Language Model Inversion](https://mlsanity.com/paper/2311.13647/) (2023)
- [DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text](https://mlsanity.com/paper/2305.05773/) (2023)
- [Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?](https://mlsanity.com/paper/2407.17417/) (2024)
- [Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs](https://mlsanity.com/paper/2407.04411/) (2024)
- [Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting](https://mlsanity.com/paper/2410.05750/) (2024)

## Abstract (arXiv)

Model stealing attacks have recently been introduced, enabling the extraction of precise information from black-box commercial language models. In this work, we propose defense methods against a recent attack of citecarlini2024stealing and extensions for extracting the hidden layer dimension of production language models. Our methods are inspired by watermarking techniques that perturb the logits layer of these models to prevent such attacks. We provide empirical experiments demonstrating the effectiveness of the proposed defense versus model quality degradation across various configurations, and propose an effective defense against such attacks while preserving model utility.