Rubén Salvador

Avenue de la Boulaie-CS 47601

35576, Cesson-Sévigné, France

Office 321

Tel: +33 299 84 45 41

This website is Work In Progress

I am an Associate Professor of Electrical and Computer Engineering at CentraleSupélec, with a reasearch appointment at the IETR (Institut d’Électronique et des Technologies du numéRique) in Rennes, France.

My research interests span the areas of embedded computing architectures, reconfigurable computing, hardware security and self-adaptive systems. I work on building reconfigurable architectures for adaptive hardware, designing and programming novel accelerator architectures and digging around with hardware security. Recently, I started working on hardware security for machine learning, specifically on side-channel attacks resistant implementations of DL hardware accelerators. Overall, my research work aims at building more efficient, secure and intelligent systems.

Previously, I was an Assistant Professor (2017–2019) and Teaching Assistant (2012–2017) at UPM (Technical University of Madrid).

I obtained my PhD (2015) in Electrical & Computer Engineering at CEI (Center of Industrial Electronics, UPM) working on evolvable hardware in FPGAs, under the supervision of Professors Eduardo de la Torre (CEI, UPM) and Lukáš Sekanina (Brno University of Technology).

Even before that I was a Research Assistant (2006–2011) at CEI, UPM, and a Research Engineer (2005–2006) at INSIA (Intelligent Vehicle Systems unit, University Institute for Automobile research, UPM).

news

Feb 13, 2022	This website is Work In Progress
Nov 7, 2015	A long announcement with details

selected publications

Appl. Sci.

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

Méndez Real, Maria, and Salvador, Rubén

Applied Sciences

Abs HTML PDF

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.