Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.10753 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910049275740160 |
|---|---|
| author | Dorfmeister, Daniel Ferrarotti, Flavio Fischer, Bernhard Schwandtner, Martin Sochor, Hannes |
| author_facet | Dorfmeister, Daniel Ferrarotti, Flavio Fischer, Bernhard Schwandtner, Martin Sochor, Hannes |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10753 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A PUF-Based Approach for Copy Protection of Intellectual Property in Neural Network Models Dorfmeister, Daniel Ferrarotti, Flavio Fischer, Bernhard Schwandtner, Martin Sochor, Hannes Cryptography and Security Machine Learning 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. |
| title | A PUF-Based Approach for Copy Protection of Intellectual Property in Neural Network Models |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2603.10753 |