Scientific Research Publishing
About: OAlib is an academic journal published by Scientific Research Publishing. The journal publishes majorly in the area(s): Medicine & Psychology. It has an ISSN identifier of 2333-9705. It is also open access. Over the lifetime, 1050 publications have been published receiving 197 citations. The journal is also known as: Open access library journal.
TL;DR: It is shown that training a network model by combining different subkeys outperforms a traditional network model trained with a single subkey, and the conclusion is proved on two well-known datasets.
Abstract: The majority of recently demonstrated Deep-Learning Side-Channel Attacks (DLSCAs) use neural networks trained on a segment of traces containing operations only related to the target subkey. However, when the number of training traces is restricted such as in the ASCAD database, deep-learning models always suffer from overfitting since the insufficient training data. One data-level solution is called data augmentation, which is to use the additional synthetically modified traces to act as a regularizer to provide a better generalization capacity for deep-learning models. In this paper, we propose a cross-subkey training approach which acts as a trace augmentation. We train deep-learning models not only on a segment of traces containing the SBox operation of the target subkey of AES-128, but also on segments for other 15 subkeys. We show that training a network model by combining different subkeys outperforms a traditional network model trained with a single subkey, and prove the conclusion on two well-known datasets.
TL;DR: Water Use Efficiency (WUE) and Crop Water Productivity (CWP) are water accounting metrics aimed at monitoring the efficiency with which water is supplied to the field and the rate at which the plant converts water into food respectively as mentioned in this paper .
Abstract: Our planet faces a challenge of producing food to meet the demand of current population which is projected to increase by the year 2050. This implies producing more food from the existing fresh water resources which are already stressed. This is because agriculture accounts for 70% global fresh water consumption; the rest is domestic and industrial use. Yet, water is unevenly distributed globally, causing some countries to be water-rich and others water-poor. Agricultural water management provides opportunities to optimize crop yield from less water. This necessitates a shift from conventional crop production approaches which aimed at maximizing yield per unit area of land to more water conscious methods that seek to maximize crop yield per unit water consumption which is determined by evapotranspiration. Water Use Efficiency (WUE) and Crop Water Productivity (CWP) are water accounting metrics aimed at monitoring the efficiency with which water is supplied to the field and the rate at which the plant converts water into food respectively. This paper reviews these metrics by examining their differences, assessing their contribution to sustainable water management, factors affecting each of them and strategies for increasing both metrics. Findings from literature suggest that WUE and CWP are different terms, but often misused especially WUE which is wrongly applied in the contexts meant for CWP. Factors affecting CWP which must be also considered in devising strategies for increasing it can be grouped into crop specific factors, climate factors and management factors. The paper recommends a number of interventions aiming at increasing WUE and CWP from local to global scale. These include provision of technical and financial support to developing counties to enable reduce water wastage, benefit from rainfall through rain harvesting technologies and low cost irrigation