# A PUF-Based Approach for Copy Protection of Intellectual Property in Neural Network Models

arXiv: https://arxiv.org/abs/2603.10753 · HTML: https://mlsanity.com/paper/2603.10753/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences](https://mlsanity.com/paper/2206.08451/) (2022)
- [Physical Unclonable Functions (PUF) for IoT Devices](https://mlsanity.com/paper/2205.08587/) (2022)
- [Device-Bind Key-Storageless Hardware AI Model IP Protection: A PUF and Permute-Diffusion Encryption-Enabled Approach](https://mlsanity.com/paper/2212.11133/) (2022)

## Abstract (arXiv)

More and more companies' Intellectual Property (IP) is being integrated into Neural Network (NN) models. This IP has considerable value for companies and, therefore, requires adequate protection. For example, an attacker might replicate a production machines' hardware and subsequently simply copy associated software and NN models onto the cloned hardware. To make copying NN models onto cloned hardware infeasible, we present an approach to bind NN models - and thus also the IP contained within them - to their underlying hardware. For this purpose, we link an NN model's weights, which are crucial for its operation, to unique and unclonable hardware properties by leveraging Physically Unclonable Functions (PUFs). By doing so, sufficient accuracy can only be achieved using the target hardware to restore the original weights, rendering proper execution of the NN model on cloned hardware impossible. We demonstrate that our approach accomplishes the desired degradation of accuracy on various NN models and outline possible future improvements.