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

2021 ◽  
Vol 11 (15) ◽  
pp. 6790
Author(s):  
Maria Méndez Real ◽  
Rubén Salvador

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.

Author(s):  
Anh-Tuan Hoang ◽  
Neil Hanley ◽  
Maire O’Neill

Deep learning (DL) has proven to be very effective for image recognition tasks, with a large body of research on various model architectures for object classification. Straight-forward application of DL to side-channel analysis (SCA) has already shown promising success, with experimentation on open-source variable key datasets showing that secret keys can be revealed with 100s traces even in the presence of countermeasures. This paper aims to further improve the application of DL for SCA, by enhancing the power of DL when targeting the secret key of cryptographic algorithms when protected with SCA countermeasures. We propose a new model, CNN-based model with Plaintext feature extension (CNNP) together with multiple convolutional filter kernel sizes and structures with deeper and narrower neural networks, which has empirically proven its effectiveness by outperforming reference profiling attack methods such as template attacks (TAs), convolutional neural networks (CNNs) and multilayer perceptron (MLP) models. Our model generates state-of-the art results when attacking the ASCAD variable-key database, which has a restricted number of training traces per key, recovering the key within 40 attack traces in comparison with order of 100s traces required by straightforward machine learning (ML) application. During the profiling stage an attacker needs no additional knowledge on the implementation, such as the masking scheme or random mask values, only the ability to record the power consumption or electromagnetic field traces, plaintext/ciphertext and the key. Additionally, no heuristic pre-processing is required in order to break the high-order masking countermeasures of the target implementation.


Author(s):  
Jaehun Kim ◽  
Stjepan Picek ◽  
Annelie Heuser ◽  
Shivam Bhasin ◽  
Alan Hanjalic

Profiled side-channel analysis based on deep learning, and more precisely Convolutional Neural Networks, is a paradigm showing significant potential. The results, although scarce for now, suggest that such techniques are even able to break cryptographic implementations protected with countermeasures. In this paper, we start by proposing a new Convolutional Neural Network instance able to reach high performance for a number of considered datasets. We compare our neural network with the one designed for a particular dataset with masking countermeasure and we show that both are good designs but also that neither can be considered as a superior to the other one.Next, we address how the addition of artificial noise to the input signal can be actually beneficial to the performance of the neural network. Such noise addition is equivalent to the regularization term in the objective function. By using this technique, we are able to reduce the number of measurements needed to reveal the secret key by orders of magnitude for both neural networks. Our new convolutional neural network instance with added noise is able to break the implementation protected with the random delay countermeasure by using only 3 traces in the attack phase. To further strengthen our experimental results, we investigate the performance with a varying number of training samples, noise levels, and epochs. Our findings show that adding noise is beneficial throughout all training set sizes and epochs.


2019 ◽  
Vol 27 (3) ◽  
pp. 651-658
Author(s):  
S. R. Hou ◽  
Y. J. Zhou ◽  
H. M. Liu

Author(s):  
Lars-Christer Hydén ◽  
Mattias Forsblad

In this chapter we consider collaborative remembering and joint activates in everyday life in the case of people living with dementia. First, we review past research of practices that scaffolds the participation of persons with dementia in everyday chores under different stages of dementia diseases. We do so by suggesting three analytical types of scaffolding: when the scaffolding practices (i) frame the activity, (ii) guide actions, or (iii) are part of repair activities. Second, we review two aspects of collaborative remembering that are especially important in the case of dementia: training of scaffolding practices, and the sustaining and presentation of identities through collaborative storytelling. Finally, theoretical and methodological tendencies of the research field are summarized and future research needs are formulated.


Games ◽  
2021 ◽  
Vol 12 (2) ◽  
pp. 45
Author(s):  
Tiziana Ciano ◽  
Massimiliano Ferrara ◽  
Mariangela Gangemi ◽  
Domenica Stefania Merenda ◽  
Bruno Antonio Pansera

This work aims to provide different perspectives on the relationships between cooperative game theory and the research field concerning climate change dynamics. New results are obtained in the framework of competitive bargaining solutions and related issues, moving from a cooperative approach to a competitive one. Furthermore, the dynamics of balanced and super-balanced games are exposed, with particular reference to coalitions. Some open problems are presented to aid future research in this area.


Author(s):  
Xiaochen Zhang ◽  
Lanxin Hui ◽  
Linchao Wei ◽  
Fuchuan Song ◽  
Fei Hu

Electric power wheelchairs (EPWs) enhance the mobility capability of the elderly and the disabled, while the human-machine interaction (HMI) determines how well the human intention will be precisely delivered and how human-machine system cooperation will be efficiently conducted. A bibliometric quantitative analysis of 1154 publications related to this research field, published between 1998 and 2020, was conducted. We identified the development status, contributors, hot topics, and potential future research directions of this field. We believe that the combination of intelligence and humanization of an EPW HMI system based on human-machine collaboration is an emerging trend in EPW HMI methodology research. Particular attention should be paid to evaluating the applicability and benefits of the EPW HMI methodology for the users, as well as how much it contributes to society. This study offers researchers a comprehensive understanding of EPW HMI studies in the past 22 years and latest trends from the evolutionary footprints and forward-thinking insights regarding future research.


Sign in / Sign up

Export Citation Format

Share Document