Neural network based attack on a masked implementation of AES

Gilmore, Richard; Hanley, Neil; O’Neill, Máire

doi:10.1109/hst.2015.7140247

Cited by 110 publications

(53 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has also been shown that first‐order masked AES can be analyzed using an MLP . For instance, Martinasek and others analyzed a masked AES software implementation using an MLP.…”

Section: Deep Learning‐based Side‐channel Analysismentioning

confidence: 99%

Recent advances in deep learning‐based side‐channel analysis

Jin

Kim

et al. 2020

ETRI Journal

View full text Add to dashboard Cite

As side‐channel analysis and machine learning algorithms share the same objective of classifying data, numerous studies have been proposed for adapting machine learning to side‐channel analysis. However, a drawback of machine learning algorithms is that their performance depends on human engineering. Therefore, recent studies in the field focus on exploiting deep learning algorithms, which can extract features automatically from data. In this study, we survey recent advances in deep learning‐based side‐channel analysis. In particular, we outline how deep learning is applied to side‐channel analysis, based on deep learning architectures and application methods. Furthermore, we describe its properties when using different architectures and application methods. Finally, we discuss our perspective on future research directions in this field.

show abstract

“…It has also been shown that first‐order masked AES can be analyzed using an MLP . For instance, Martinasek and others analyzed a masked AES software implementation using an MLP.…”

Section: Deep Learning‐based Side‐channel Analysismentioning

confidence: 99%

Recent advances in deep learning‐based side‐channel analysis

Jin

Kim

et al. 2020

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…In the past couple of years, several ML techniques have been investigated, including but not limited to support vector machines (SVM) [16], [17], random forests (RF) [17]. More recently, the signal processing community as well as the hardware security researchers have started exploring the field of Deep Neural Networks (DNNs) [10], [30].…”

Section: Background and Literature Reviewmentioning

confidence: 99%

“…To the best of our knowledge, both data sets consist of traces captured from one single device, which are not suitable for current work. Hence, we collected new traces from 30 different 8-bit AVR microcontrollers running [10], [30], [19], [18], [20], [31] Cross-device Attack Template Attack [14], [13], [32], [15] Neural Networks [21], [22], This Work the AES-128 algorithm using the ChipWhisperer platform [24] (Figure 2). Although 8-bit microcontrollers are becoming less preferred for encryption engines nowadays, recent body of work ( [13], [18], [37], [38], [39]) investigated performance of Profiled SCA attack using datasets gathered from 8-bit microcontrollers.…”

Section: A Related Workmentioning

confidence: 99%

Practical Approaches Toward Deep-Learning-Based Cross-Device Power Side-Channel Attack

Golder

Das

Danial

et al. 2019

IEEE Trans. VLSI Syst.

View full text Add to dashboard Cite

Power side-channel analysis (SCA) has been of immense interest to most embedded designers to evaluate the physical security of the system. This work presents profiling-based cross-device power SCA attacks using deep learning techniques on 8-bit AVR microcontroller devices running AES-128. Firstly, we show the practical issues that arise in these profiling-based cross-device attacks due to significant device-to-device variations. Secondly, we show that utilizing Principal Component Analysis (PCA) based pre-processing and multi-device training, a Multi-Layer Perceptron (MLP) based 256-class classifier can achieve an average accuracy of 99.43% in recovering the first key byte from all the 30 devices in our data set, even in the presence of significant inter-device variations. Results show that the designed MLP with PCA-based pre-processing outperforms a Convolutional Neural Network (CNN) with 4-device training by ∼ 20% in terms of the average test accuracy of cross-device attack for the aligned traces captured using the ChipWhisperer hardware. Finally, to extend the practicality of these cross-device attacks, another preprocessing step, namely, Dynamic Time Warping (DTW) has been utilized to remove any misalignment among the traces, before performing PCA. DTW along with PCA followed by the 256-class MLP classifier provides ≥10.97% higher accuracy than the CNN based approach for cross-device attack even in the presence of up to 50 time-sample misalignments between the traces.

show abstract

“…We take 50 features for ML techniques since we use large datasets and the number of features is one of two factors (the second one being the number of measurements) comprising the time complexity for ML algorithms. Additionally, 50 features is also taken in the literature as the design choice [12,14]. To select those features, we use Pearson correlation coefficient where we calculate it for the target class variables HW, which consists of categorical values that are interpreted as numerical values [39]:…”

Section: Data Preparation and Parameter Tuningmentioning

confidence: 99%

“…Machine learning (ML) is a term encompassing a number of methods that can be used for tasks like clustering, classification, regression, feature selection, etc [7]. Consequently, SCA community started to experiment with different ML techniques and to evaluate whether they are useful in the SCA context, see e.g., [4,[8][9][10][11][12][13][14][15][16][17]. Although considering different scenarios and often different ML techniques (with some algorithms used in prevailing number of papers like Support Vector Machines and Random Forest), all those papers have in common that they establish numerous scenarios where ML techniques can outperform template attack and are the best choice for profiled SCA.…”

Section: Introductionmentioning

confidence: 99%

On the Performance of Convolutional Neural Networks for Side-Channel Analysis

Picek

Samiotis

Heuser

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we ask a question whether convolutional neural networks are more suitable for SCA scenarios than some other machine learning techniques, and if yes, in what situations. Our results point that convolutional neural networks indeed outperforms machine learning in several scenarios when considering accuracy. Still, often there is no compelling reason to use such a complex technique. In fact, if comparing techniques without extra steps like preprocessing, we see an obvious advantage for convolutional neural networks only when the level of noise is small, and the number of measurements and features is high. The other tested settings show that simpler machine learning techniques, for a significantly lower computational cost, perform similar or even better. The experiments with the guessing entropy metric indicate that simpler methods like Random forest or XGBoost perform better than convolutional neural networks for the datasets we investigated. Finally, we conduct a small experiment that opens the question whether convolutional neural networks are actually the best choice in side-channel analysis context since there seems to be no advantage in preserving the topology of measurements.

show abstract

Neural network based attack on a masked implementation of AES

Cited by 110 publications

References 20 publications

Recent advances in deep learning‐based side‐channel analysis

Recent advances in deep learning‐based side‐channel analysis

Practical Approaches Toward Deep-Learning-Based Cross-Device Power Side-Channel Attack

On the Performance of Convolutional Neural Networks for Side-Channel Analysis

Contact Info

Product

Resources

About