COVID-19 drastically raised the importance of non-contact based healthcare methods. Low blood oxygen levels of a person, which can be unnoticeable, are potentially a precursor of COVID-19. Contact based methods for measuring blood oxygen saturation could spread the contagious disease. Therefore, this paper investigates non-contact RGB camera-based peripheral oxygen saturation estimation by remote photoplethysmography (rPPG) methods. The novel aspects of non-contact oxygen saturation that we are looking into are: (1) Applying SpO$_2$ predictor neural networks to rPPG signals obtained from facial regions, instead of the less practical hand based skin regions. To be more specific, we show in a facial based setting that in the relatively uncontrolled environment the traditional Ratio-of-Ratios pulse oximetry principles fail. In the leave-one-participant-out experiments, the RoR method achieved a correlation of $-0.05$, whereas neural networks showed the capability of dealing with the inherent challenges of the PURE dataset by achieving a superior correlation of $0.64$. These challenges are lighting variation due to subtle head motion and clouds alternatively blocking the sun. (2) The first end-to-end neural networks for SpO$_2$ estimation are introduced by replacing traditional hard pixel region-of-interest selectors, which assign equal weight to each selected pixel, with convolutional soft-attention masks. (3) By using an adapted version of a recent heart and breathing rate estimator network, called DeepPhys, we indicate that the current state-of-the-art is far from optimal. This is done by comparing the window-based constructed end-to-end neural networks with Adapted DeepPhys, which is based on single frame differences. Finally, our research\footnote{Code available on \url{https://github.com/jimkok9/oxygenSaturation}} shows that non-contact facial based SpO$_2$ estimation by RGB camera remains a difficult task. However, as our results indicate, more sophisticated deep learning model might become a viable diagnostic tool for this task in the future.

Analysing physical leakages (e.g. power consumption and electromagnetic radiation) of cryptographic devices can be used by adversaries to extract secret keys. Over the last couple of years, researchers have shown that machine learning has potential for this process. Machine learning models need to be fine-tuned to enhance key extraction performance. This paper investigates the so-called dropout hyper-parameter, which is proven to reduce overfitting in various domains (e.g. speech recognition). Dropout is examined for two different models: multilayer perceptrons and convolutional neural networks. Regarding the convolutional neural networks, two architectures are examined: one architecture used as a benchmark in various papers and a more uncomplicated one. The findings of this paper showed that adding dropout to the investigated multilayer perceptron architecture led to significant improvements, whereas the convolutional neural network architectures showed negligible improvements.