TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments
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_ | 1866913343267143680 |
|---|---|
| author | Liu, Ziyu Zhou, Tong Luo, Yukui Xu, Xiaolin |
| author_facet | Liu, Ziyu Zhou, Tong Luo, Yukui Xu, Xiaolin |
| contents | Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or introduce large performance overhead. Taking both security and performance into consideration, this paper presents TBNet, a TEE-based defense framework that protects DNN model from a neural architectural perspective. Specifically, TBNet generates a novel Two-Branch substitution model, to respectively exploit (1) the computational resources in the untrusted Rich Execution Environment (REE) for latency reduction and (2) the physically-isolated TEE for model protection. Experimental results on a Raspberry Pi across diverse DNN model architectures and datasets demonstrate that TBNet achieves efficient model protection at a low cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03974 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments Liu, Ziyu Zhou, Tong Luo, Yukui Xu, Xiaolin Cryptography and Security Artificial Intelligence Machine Learning Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or introduce large performance overhead. Taking both security and performance into consideration, this paper presents TBNet, a TEE-based defense framework that protects DNN model from a neural architectural perspective. Specifically, TBNet generates a novel Two-Branch substitution model, to respectively exploit (1) the computational resources in the untrusted Rich Execution Environment (REE) for latency reduction and (2) the physically-isolated TEE for model protection. Experimental results on a Raspberry Pi across diverse DNN model architectures and datasets demonstrate that TBNet achieves efficient model protection at a low cost. |
| title | TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.03974 |