THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929729999732736 |
|---|---|
| author | Dizani, Farshad Ghanbari, Azam Kalyanapu, Joshua Asher, Darsh Ajorpaz, Samira Mirbagher |
| author_facet | Dizani, Farshad Ghanbari, Azam Kalyanapu, Joshua Asher, Darsh Ajorpaz, Samira Mirbagher |
| contents | The rise of on-chip accelerators signifies a major shift in computing, driven by the growing demands of artificial intelligence (AI) and specialized applications. These accelerators have gained popularity due to their ability to substantially boost performance, cut energy usage, lower total cost of ownership (TCO), and promote sustainability. Intel's Advanced Matrix Extensions (AMX) is one such on-chip accelerator, specifically designed for handling tasks involving large matrix multiplications commonly used in machine learning (ML) models, image processing, and other computational-heavy operations. In this paper, we introduce a novel value-dependent timing side-channel vulnerability in Intel AMX. By exploiting this weakness, we demonstrate a software-based, value-dependent timing side-channel attack capable of inferring the sparsity of neural network weights without requiring any knowledge of the confidence score, privileged access or physical proximity. Our attack method can fully recover the sparsity of weights assigned to 64 input elements within 50 minutes, which is 631% faster than the maximum leakage rate achieved in the Hertzbleed attack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17658 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX Dizani, Farshad Ghanbari, Azam Kalyanapu, Joshua Asher, Darsh Ajorpaz, Samira Mirbagher Cryptography and Security Hardware Architecture The rise of on-chip accelerators signifies a major shift in computing, driven by the growing demands of artificial intelligence (AI) and specialized applications. These accelerators have gained popularity due to their ability to substantially boost performance, cut energy usage, lower total cost of ownership (TCO), and promote sustainability. Intel's Advanced Matrix Extensions (AMX) is one such on-chip accelerator, specifically designed for handling tasks involving large matrix multiplications commonly used in machine learning (ML) models, image processing, and other computational-heavy operations. In this paper, we introduce a novel value-dependent timing side-channel vulnerability in Intel AMX. By exploiting this weakness, we demonstrate a software-based, value-dependent timing side-channel attack capable of inferring the sparsity of neural network weights without requiring any knowledge of the confidence score, privileged access or physical proximity. Our attack method can fully recover the sparsity of weights assigned to 64 input elements within 50 minutes, which is 631% faster than the maximum leakage rate achieved in the Hertzbleed attack. |
| title | THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX |
| topic | Cryptography and Security Hardware Architecture |
| url | https://arxiv.org/abs/2502.17658 |