Next Article in Journal
Effects of Complex Electromagnetic Fields on Candida albicans Adhesion and Proliferation on Polyacrylic Resin
Next Article in Special Issue
Balancing the Leakage Currents in Nanometer CMOS Logic—A Challenging Goal
Previous Article in Journal
Automotive OEM Demand Forecasting: A Comparative Study of Forecasting Algorithms and Strategies
Previous Article in Special Issue
Performing Cache Timing Attacks from the Reconfigurable Part of a Heterogeneous SoC—An Experimental Study
Review

Physical Side-Channel Attacks on Embedded Neural Networks: A Survey

1
Univ Nantes, CNRS, IETR UMR 6164, F-44000 Nantes, France
2
CentraleSupélec, CNRS, IETR UMR 6164, F-35576 Cesson-Sévigné, France
*
Author to whom correspondence should be addressed.
Academic Editor: Luigi Pomante
Appl. Sci. 2021, 11(15), 6790; https://doi.org/10.3390/app11156790
Received: 25 June 2021 / Revised: 15 July 2021 / Accepted: 21 July 2021 / Published: 23 July 2021
(This article belongs to the Special Issue Side Channel Attacks in Embedded Systems)
During the last decade, Deep Neural Networks (DNN) have progressively been integrated on all types of platforms, from data centers to embedded systems including low-power processors and, recently, FPGAs. Neural Networks (NN) are expected to become ubiquitous in IoT systems by transforming all sorts of real-world applications, including applications in the safety-critical and security-sensitive domains. However, the underlying hardware security vulnerabilities of embedded NN implementations remain unaddressed. In particular, embedded DNN implementations are vulnerable to Side-Channel Analysis (SCA) attacks, which are especially important in the IoT and edge computing contexts where an attacker can usually gain physical access to the targeted device. A research field has therefore emerged and is rapidly growing in terms of the use of SCA including timing, electromagnetic attacks and power attacks to target NN embedded implementations. Since 2018, research papers have shown that SCA enables an attacker to recover inference models architectures and parameters, to expose industrial IP and endangers data confidentiality and privacy. Without a complete review of this emerging field in the literature so far, this paper surveys state-of-the-art physical SCA attacks relative to the implementation of embedded DNNs on micro-controllers and FPGAs in order to provide a thorough analysis on the current landscape. It provides a taxonomy and a detailed classification of current attacks. It first discusses mitigation techniques and then provides insights for future research leads. View Full-Text
Keywords: physical side-channel attacks; Side-Channel Analysis; hardware security; machine learning; Embedded Neural Networks; Deep Neural Networks physical side-channel attacks; Side-Channel Analysis; hardware security; machine learning; Embedded Neural Networks; Deep Neural Networks
Show Figures

Figure 1

MDPI and ACS Style

Méndez Real, M.; Salvador, R. Physical Side-Channel Attacks on Embedded Neural Networks: A Survey. Appl. Sci. 2021, 11, 6790. https://doi.org/10.3390/app11156790

AMA Style

Méndez Real M, Salvador R. Physical Side-Channel Attacks on Embedded Neural Networks: A Survey. Applied Sciences. 2021; 11(15):6790. https://doi.org/10.3390/app11156790

Chicago/Turabian Style

Méndez Real, Maria, and Rubén Salvador. 2021. "Physical Side-Channel Attacks on Embedded Neural Networks: A Survey" Applied Sciences 11, no. 15: 6790. https://doi.org/10.3390/app11156790

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop