Methodology for Efficient CNN Architectures in Profiling Attacks

Abstract

The side-channel community recently investigated a new approach, based on deep learning, to significantly improve profiled attacks against embedded systems. Previous works have shown the benefit of using convolutional neural networks (CNN) to limit the effect of some countermeasures such as desynchronization. Compared with template attacks, deep learning techniques can deal with trace misalignment and the high dimensionality of the data. Pre-processing is no longer mandatory. However, the performance of attacks depends to a great extent on the choice of each hyperparameter used to configure a CNN architecture. Hence, we cannot perfectly harness the potential of deep neural networks without a clear understanding of the network’s inner-workings. To reduce this gap, we propose to clearly explain the role of each hyperparameters during the feature selection phase using some specific visualization techniques including Weight Visualization, Gradient Visualization and Heatmaps. By highlighting which features are retained by filters, heatmaps come in handy when a security evaluator tries to interpret and understand the efficiency of CNN. We propose a methodology for building efficient CNN architectures in terms of attack efficiency and network complexity, even in the presence of desynchronization. We evaluate our methodology using public datasets with and without desynchronization. In each case, our methodology outperforms the previous state-of-the-art CNN models while significantly reducing network complexity. Our networks are up to 25 times more efficient than previous state-of-the-art while their complexity is up to 31810 times smaller. Our results show that CNN networks do not need to be very complex to perform well in the side-channel context.

Numerical Evaluation on Parametric Choices Influencing Segmentation Results in Radiology Images—A Multi-Dataset Study

“…From both the experiments, we propose few of the combinations that may work better for segmentation results although it is hard to make a concise conclusion from the values in quality matrices. In best of our knowledge, there is no best algorithm proposed for the purpose of generalised medical image segmentation, but studies show that there can be best choices we can make while designing the architecture [22][23][24]. From our experimental results, we have observed that two of the combinations with Xavier weight initialization (also known as Glorot), Adam optimiser, Cross Entropy loss (Glo Adam CE ) and LeCun weight initialization, cross entropy loss and Adam optimiser Lec Adam CE worked best for most of the metrics in 3D-UNet setting, while Xavier together with cross entropy loss and Tanh activation function (Glo tanh CE ) worked best for VGG-16 network.…”

“…Reference [21] demonstrated the impact of choosing the right activation function on training dynamics and model performance. In [22], the authors proposed a strategy for the selection of hyperparameters that includes learnable parameters such as weights and biases of each layer, including the number of filters, strides, kernel sizes and the number of units per layer. In [23], the authors worked on studying different loss functions used in deep neural networks with the objective of knowing the impact of particular choices in learning dynamics for classification as a task.…”

Online Performance Evaluation of Deep Learning Networks for Profiled Side-Channel Analysis

“…The main advantage of the filters and convolutional layers is their time-invariance property that allows the network to be robust against desynchronization (e.g. shifting, jitter) [3,16]. Therefore, the resynchronization pre-processing is not necessary anymore.…”

“…As a consequence, the network is able to estimate functions F much more complex than the optimal one. To reduce the impact of overfitting, some techniques can be used such as data augmentation [3], noise addition [7], regularization or a more fitting architecture [16].…”

“…Very similar to profiling attacks, deep learning algorithms were inevitably applied in the side-channel context. Indeed, some articles have shown the robustness of convolutional neural networks (CNNs) to the most common countermeasures, namely masking [10,11] and desynchronization [3,16]. One of their main advantages is that they do not require pre-processing of the traces.…”