For the dramatic increase of Android malware and low efficiency of manual check process, deep learning methods started to be an auxiliary means for Android malware detection these years. However, these models are highly dependent on the quality of datasets, and perform unsatisfactory results when the quality of training data is not good enough. In the real world, the quality of datasets without manually check cannot be guaranteed, even Google Play may contain malicious applications, which will cause the trained model failure. To address the challenge, we propose a robust Android malware detection approach based on selective ensemble learning, trying to provide an effective solution not that limited to the quality of datasets. The proposed model utilizes genetic algorithm to help find the best combination of the component learners and improve robustness of the model. Our results show that the proposed approach achieves a more robust performance than other approaches in the same area. CCS CONCEPTS• Security and privacy → Software and application security;• Computing methodologies → Neural networks.

This paper proposes a method of establishing flight path planning surrogate model based on stacking ensemble learning, which can solve the real-time problem of complex flight mission’s on-line waypoints calculation. Airborne navigation system mainly utilizes several discrete waypoints to guide flight path or flight control. These waypoints are usually calculated by a set of equations based on flight dynamics, flight kinematics and flight mission constraints, and therefore path planning for complex missions cannot guarantee real-time performance. In this paper, flight samples are generated offline by taking flight mission characteristic parameters as input and flight waypoint coordinate series as output. Then two-layer coupling model is constructed based on stacking ensemble learning. A series of base-learners are constructed to learn the quantity of waypoints or each waypoint’s coordinate values respectively. At last, flight path planning surrogate model is built by combining all the base-learners, establishing the direct mapping relationship between input and output. The results show that this surrogate model can effectively calculate the aircraft flight waypoints, and meanwhile maintains ideal accuracy and real-time performance.