With the popularisation of Android smartphones, the value of mobile application security research has increased. The emergence of adversarial technology makes it possible for malware to evade detection. Therefore, research is conducted on Android malicious applications of adversarial attack. To clarify the process and theory of adversarial sample generation, an adversarial sample generation algorithm is proposed that filters features based on feature spatial distribution and definition. These features are modified on real malicious samples to form adversarial samples. In addition, to enhance the robustness of adversarial sample classification detection, a multiple feature set detection algorithm is designed and implemented. Using the frequency differential enhancement feature selection algorithm to perform feature screening, the algorithm forms two different feature sets and establishes two different training sets to train different classification algorithms. Prediction results obtained by the two classification algorithms are integrated based on certain rules. Experimental results on the VirusShare dataset show that both algorithms are effective. The detection results in an actual environment also prove the effectiveness of the multiple feature set detection algorithm.

Unbalanced data in intrusion detection seriously affect the overall performance of intrusion detection methods. This paper proposes an intrusion detection algorithm based on unbalanced learning (ID-UL) for unbalanced learning. It uses two strategies to address the issues brought about by unbalanced data. First, the data grouping strategy based on integrated learning alleviates the extreme data imbalance and avoids the negative impact on imbalanced learning. Meanwhile, to avoid the possible negative impact brought by unbalanced data on the learning procedures of convolutional neural networks, the strategy of assigning weight to the loss function is adopted. Besides, a method for determining the weight value is designed to make the model supervise the learning of attack samples during the training process. Experimental results on the NSL-KDD dataset show that the method in this paper can effectively improve the detection of attack classes, and the overall detection accuracy reaches 81.48%. ID-UL has the same significant effect on other imbalanced datasets.