Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.07783 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929522560991232 |
|---|---|
| author | Horvath, Peter Chmielewski, Lukasz Weissbart, Leo Batina, Lejla Yarom, Yuval |
| author_facet | Horvath, Peter Chmielewski, Lukasz Weissbart, Leo Batina, Lejla Yarom, Yuval |
| contents | Over the last decade, applications of neural networks (NNs) have spread to various aspects of our lives. A large number of companies base their businesses on building products that use neural networks for tasks such as face recognition, machine translation, and self-driving cars. Much of the intellectual property underpinning these products is encoded in the exact parameters of the neural networks. Consequently, protecting these is of utmost priority to businesses. At the same time, many of these products need to operate under a strong threat model, in which the adversary has unfettered physical control of the product. In this work, we present BarraCUDA, a novel attack on general purpose Graphic Processing Units (GPUs) that can extract parameters of neural networks running on the popular Nvidia Jetson Nano device. BarraCUDA uses correlation electromagnetic analysis to recover parameters of real-world convolutional neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07783 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | BarraCUDA: Edge GPUs do Leak DNN Weights Horvath, Peter Chmielewski, Lukasz Weissbart, Leo Batina, Lejla Yarom, Yuval Cryptography and Security Over the last decade, applications of neural networks (NNs) have spread to various aspects of our lives. A large number of companies base their businesses on building products that use neural networks for tasks such as face recognition, machine translation, and self-driving cars. Much of the intellectual property underpinning these products is encoded in the exact parameters of the neural networks. Consequently, protecting these is of utmost priority to businesses. At the same time, many of these products need to operate under a strong threat model, in which the adversary has unfettered physical control of the product. In this work, we present BarraCUDA, a novel attack on general purpose Graphic Processing Units (GPUs) that can extract parameters of neural networks running on the popular Nvidia Jetson Nano device. BarraCUDA uses correlation electromagnetic analysis to recover parameters of real-world convolutional neural networks. |
| title | BarraCUDA: Edge GPUs do Leak DNN Weights |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2312.07783 |