Through the years, the market for mobile devices has been rapidly increasing, and as a result of this trend, mobile malware has become sophisticated. Researchers are focused on the design and development of malware detection systems to strengthen the security and integrity of sensitive and private information. In this context, deep learning is exploited, also in cybersecurity, showing the ability to build models aimed at detecting whether an application is Trusted or malicious. Recently, with the introduction of quantum computing, we have been witnessing the introduction of quantum algorithms in Machine Learning. In this paper, we provide a comparison between five state-of-the-art Convolutional Neural Network models (i.e., AlexNet, MobileNet, EfficientNet, VGG16, and VGG19), one network developed by the authors (called Standard-CNN), and two quantum models (i.e., a hybrid quantum model and a fully quantum neural network) to classify malware. In addition to the classification, we provide explainability behind the model predictions, by adopting the Gradient-weighted Class Activation Mapping to highlight the areas of the image obtained from the application symptomatic of a certain prediction, to the convolutional and to the quantum models obtaining the best performances in Android malware detection. Real-world experiments were performed on a dataset composed of 8446 Android malicious and legitimate applications, obtaining interesting results.

The Android operating system has been dominating the smart devices market in recent years. Smart home devices are populating our houses and smartphones are indispensable companions in daily life activities. In such a technological environment, the amount of data and user information shared across these devices is enormous and attractive for every malicious user. Consequently, developing good malware detection techniques is a crucial open problem to keep using these devices safely. This paper proposes the application of a formal methods based approach to detect banking malware in the Android environment. The experimental results are really promising, as demonstrated by the evaluation on real-world Android applications, where we reached precision and recall equal to 1.