Abstract
The appearance of deep neural networks for Side-Channel leads to strong power analysis techniques for detecting secret information of physical cryptography implementations. Generally, deep learning techniques do not suffer the difficulties of template attacks such as trace misalignment. However, the generalization of a trained deep neural network that can accurately predict Side-Channel leakages largely depends on its adjustable variables (parameters of a neural network). Although pre-training is no longer mandatory, it is needed for parameter selection of a deep neural network to improve the success rate and provide a better insight into the network’s inner functionality. In this paper, we propose a novel model via Twin support vector with a deep kernel approach when targeting a hardware implementation of AES-128. The proposed model is pre-trained with the Restricted Boltzmann Machine method in a layer-wise manner and then fine-tuned via gradient descent. Further, we used the grid search technique for the selection of each hyperparameter which is used to compute class probabilities of every test trace in our deep model based side-channel attack. Based on our analysis and experiments, this model empirically shows its effectiveness by outperforming some of its competitors in profiling attack methods such as convolutional neural networks and multilayer perceptron models. We also evaluate our model on both masked and unmasked AES implementation. The results indicate that the proposed approach has achieved a success rate of greater than 99% even with a single trace using Keras library with Tensorflow. We investigate the correct “key rank” according to the number of traces; our model reaches the key $ rank\leq 10 $ when attacking the third AES SBox.
Highlights
In the field of security and cryptography, Side-Channel Analysis (SCA) is a powerful attack that benefits from any leakage of a system such as power consumption and electromagnetic (EM) radiations, to retrieve the secret information [1]
We propose a novel and powerful deep learning model, "Deep Kernel learning Twin Support vector machine" (Deep K-TSVM) which is a great combination of deep neural network and Twin support vector machine (TSVM) classifier
The 5-layer convolutional neural networks (CNNs) performs better than the other ones except for our proposed model. 5-layer CNN requires about 200 power traces to reach a stable key guess while the CNN-SVM requires at least 400 attack traces to reach a stable key guess, it has a better performance than Multilayer perceptron (MLP) with the Principal Component Analysis (PCA) model and the NeuroSVM
Summary
In the field of security and cryptography, Side-Channel Analysis (SCA) is a powerful attack that benefits from any leakage of a system such as power consumption and electromagnetic (EM) radiations, to retrieve the secret information [1]. Note that each trace generally includes a large number of sample points which make the attack very costly, points of interest are selected which are samples with the most informative leakage from the device Another powerful subset of profiling attacks is a side-channel attack that uses Machine Learning (ML) approaches [3]. They solved the problem by inserting noise to the input traces or inserting random delays through dummy operation These publications provide a good insight on how to deal with side-channel attacks challenges using deep learning models, none of them have investigated the relation between initial parameters and the pre-training stage for generalization problems.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
