Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2501.14512 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915120172498944 |
|---|---|
| author | Liu, Zhuoran van Hoek, Senna Horváth, Péter Lauret, Dirk Xu, Xiaoyun Batina, Lejla |
| author_facet | Liu, Zhuoran van Hoek, Senna Horváth, Péter Lauret, Dirk Xu, Xiaoyun Batina, Lejla |
| contents | Neural networks have become a fundamental component of numerous practical applications, and their implementations, which are often accelerated by hardware, are integrated into all types of real-world physical devices. User interactions with neural networks on hardware accelerators are commonly considered privacy-sensitive. Substantial efforts have been made to uncover vulnerabilities and enhance privacy protection at the level of machine learning algorithms, including membership inference attacks, differential privacy, and federated learning. However, neural networks are ultimately implemented and deployed on physical devices, and current research pays comparatively less attention to privacy protection at the implementation level. In this paper, we introduce a generic physical side-channel attack, ScaAR, that extracts user interactions with neural networks by leveraging electromagnetic (EM) emissions of physical devices. Our proposed attack is implementation-agnostic, meaning it does not require the adversary to possess detailed knowledge of the hardware or software implementations, thanks to the capabilities of deep learning-based side-channel analysis (DLSCA). Experimental results demonstrate that, through the EM side channel, ScaAR can effectively extract the class label of user interactions with neural classifiers, including inputs and outputs, on the AMD-Xilinx MPSoC ZCU104 FPGA and Raspberry Pi 3 B. In addition, for the first time, we provide side-channel analysis on edge Large Language Model (LLM) implementations on the Raspberry Pi 5, showing that EM side channel leaks interaction data, and different LLM tokens can be distinguishable from the EM traces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14512 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-world Edge Neural Network Implementations Leak Private Interactions Through Physical Side Channel Liu, Zhuoran van Hoek, Senna Horváth, Péter Lauret, Dirk Xu, Xiaoyun Batina, Lejla Cryptography and Security Neural networks have become a fundamental component of numerous practical applications, and their implementations, which are often accelerated by hardware, are integrated into all types of real-world physical devices. User interactions with neural networks on hardware accelerators are commonly considered privacy-sensitive. Substantial efforts have been made to uncover vulnerabilities and enhance privacy protection at the level of machine learning algorithms, including membership inference attacks, differential privacy, and federated learning. However, neural networks are ultimately implemented and deployed on physical devices, and current research pays comparatively less attention to privacy protection at the implementation level. In this paper, we introduce a generic physical side-channel attack, ScaAR, that extracts user interactions with neural networks by leveraging electromagnetic (EM) emissions of physical devices. Our proposed attack is implementation-agnostic, meaning it does not require the adversary to possess detailed knowledge of the hardware or software implementations, thanks to the capabilities of deep learning-based side-channel analysis (DLSCA). Experimental results demonstrate that, through the EM side channel, ScaAR can effectively extract the class label of user interactions with neural classifiers, including inputs and outputs, on the AMD-Xilinx MPSoC ZCU104 FPGA and Raspberry Pi 3 B. In addition, for the first time, we provide side-channel analysis on edge Large Language Model (LLM) implementations on the Raspberry Pi 5, showing that EM side channel leaks interaction data, and different LLM tokens can be distinguishable from the EM traces. |
| title | Real-world Edge Neural Network Implementations Leak Private Interactions Through Physical Side Channel |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2501.14512 |