Deep K-TSVM: A Novel Profiled Power Side-Channel Attack on AES-128

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 layerwise 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 ≤ 10 when attacking the third AES SBox.

Decentralized Blockchain Network for Resisting Side-Channel Attacks in Mobility-Based IoT

“…The authors have used cloud-based gate arrays to investigate the vulnerabilities using a Bayesian neural network. A study on power attacks has also been carried out by Ghandali et al [28] using a combination of asymmetric encryption and a deep learning approach. The technique used asymmetric encryption via hardware implementation, wherein the Boltzmann learning technique is used for learning the probability of intrusion.…”

“…(iii) The proposed scheme facilitates the verification of adjacent nodes as well as all other actors in a non-iterative way, which acts as a dual layer of security and increases the frequency of authentication suitable for an extensive dynamic network, unlike the existing approaches , which assess only single target nodes. iv) The proposed scheme is capable of resisting differential fault attacks, power-based attacks, timing attacks and cache attacks, which opens up many opportunities for fighting multiple variants of side-channel attacks, whereas existing approaches [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] are reported to resist only singular forms of attack.…”

Deep Learning Method for Power Side-Channel Analysis on Chip Leakages

“…It would be beneficial for deep learning-based side channel attack (DLSCA) to include deeper learning. Recent studies have shown that supervised machine learning (SML) can adapt deep learning features to improve the accuracy of key retrieval and classification [4]. In a number of different trials, deep learning has been shown to be more effective than side-channel attacks.…”