Android is increasingly being targeted by malware since it has become the most popular mobile operating system worldwide. Evasive malware families, such as Chamois, designed to turn Android devices into bots that form part of a larger botnet are becoming prevalent. This calls for more effective methods for detection of Android botnets. Recently, deep learning has gained attention as a machine learning based approach to enhance Android botnet detection. However, studies that extensively investigate the efficacy of various deep learning models for Android botnet detection are currently lacking. Hence, in this paper we present a comparative study of deep learning techniques for Android botnet detection using 6802 Android applications consisting of 1929 botnet applications from the ISCX botnet dataset. We evaluate the performance of several deep learning techniques including: CNN, DNN, LSTM, GRU, CNN-LSTM, and CNN-GRU models using 342 static features derived from the applications. In our experiments, the deep learning models achieved state-of-the-art results based on the ISCX botnet dataset and also outperformed the classical machine learning classifiers.

In this paper, we address the problem of minimizing the total daily energy cost in a smart residential building composed of multiple smart homes with the aim of reducing the cost of energy bills and the greenhouse gas emissions under different system constraints and user preferences. As the household appliances contribute significantly to the energy consumption of the smart houses, it is possible to decrease electricity cost in buildings by scheduling the operation of domestic appliances. In this paper, we propose an optimization model for jointly minimizing electricity costs and CO₂ emissions by considering consumer preferences in smart buildings that are equipped with distributed energy resources (DERs). Both controllable and uncontrollable tasks and DER operations are scheduled according to the real-time price of electricity and a peak demand charge to reduce the peak demand on the grid. We formulate the daily energy consumption scheduling problem in multiple smart homes from economic and environmental perspectives and exploit a mixed integer linear programming technique to solve it. We validated the proposed approach through extensive experimental analysis. The results of the experiment show that the proposed approach can decrease both CO₂ emissions and the daily energy cost.

The threat of malware in the Internet of Things (IoT) is ever-present given that many IoT systems today rely on the Android operating system. There has been a consistent rise in Android malware recently, with new variants adopting sophisticated detection avoidance techniques, including various forms of obfuscation. Hence, there is a need to improve the effectiveness of Android malware detection as obfuscation becomes more prevalent in the wild. In this article, we present a novel approach for obfuscated malware detection in IoT Android applications based on the visualization of app executables with Markov images. The app images are trained using a convolutional neural network (CNN) to detect obfuscated malware and for the identification of the obfuscation type. We evaluate the performance of the proposed system by experimenting with four different classification models using 12000 Android applications. The CNN model created to distinguish between malware and benign apps obtained an accuracy of 99.41%. The model for identifying obfuscated malware from benign applications obtained 99.65% accuracy while the model created to identify obfuscated malware from non-obfuscated malware yielded an accuracy of 99.81%. The model for classifying obfuscated malware into 14 different obfuscation categories obtained an accuracy of 99.67%. These results show that CNN models trained from Markov images generated using application byte code can be highly effective for obfuscated malware detection and classification. Moreover, our proposed system provides a more sustainable and cost-effective method for obfuscated malware detection compared to the manual feature-engineering-based approaches that are more prevalent in the current literature.