Side-Channel Analysis of OpenVINO-based Neural Network Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917753413173248 |
|---|---|
| author | Jap, Dirmanto Breier, Jakub Lehocký, Zdenko Bhasin, Shivam Hou, Xiaolu |
| author_facet | Jap, Dirmanto Breier, Jakub Lehocký, Zdenko Bhasin, Shivam Hou, Xiaolu |
| contents | Embedded devices with neural network accelerators offer great versatility for their users, reducing the need to use cloud-based services. At the same time, they introduce new security challenges in the area of hardware attacks, the most prominent being side-channel analysis (SCA). It was shown that SCA can recover model parameters with a high accuracy, posing a threat to entities that wish to keep their models confidential. In this paper, we explore the susceptibility of quantized models implemented in OpenVINO, an embedded framework for deploying neural networks on embedded and Edge devices. We show that it is possible to recover model parameters with high precision, allowing the recovered model to perform very close to the original one. Our experiments on GoogleNet v1 show only a 1% difference in the Top 1 and a 0.64% difference in the Top 5 accuracies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16467 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Side-Channel Analysis of OpenVINO-based Neural Network Models Jap, Dirmanto Breier, Jakub Lehocký, Zdenko Bhasin, Shivam Hou, Xiaolu Cryptography and Security Artificial Intelligence Embedded devices with neural network accelerators offer great versatility for their users, reducing the need to use cloud-based services. At the same time, they introduce new security challenges in the area of hardware attacks, the most prominent being side-channel analysis (SCA). It was shown that SCA can recover model parameters with a high accuracy, posing a threat to entities that wish to keep their models confidential. In this paper, we explore the susceptibility of quantized models implemented in OpenVINO, an embedded framework for deploying neural networks on embedded and Edge devices. We show that it is possible to recover model parameters with high precision, allowing the recovered model to perform very close to the original one. Our experiments on GoogleNet v1 show only a 1% difference in the Top 1 and a 0.64% difference in the Top 5 accuracies. |
| title | Side-Channel Analysis of OpenVINO-based Neural Network Models |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2407.16467 |