In the malware detection process, obfuscated malicious codes cannot be efficiently and accurately detected solely in the dynamic or static feature space. Aiming at this problem, an integrative feature extraction algorithm based on simhash was proposed, which combines the static information e.g., API (Application Programming Interface) calls and dynamic information (such as file, registry and network behaviors) of malicious samples to form integrative features. The experiment extracts the integrative features of some static information and dynamic information, and then compares the classification, time and obfuscated-detection performance of the static, dynamic and integrated features, respectively, by using several common machine learning algorithms. The results show that the integrative features have better time performance than the static features, and better classification performance than the dynamic features, and almost the same obfuscated-detection performance as the dynamic features. This algorithm can provide some support for feature extraction of malware detection.

This paper introduces a dynamic multiple digital watermarking model based on a formal characterization of time-series in terms of temporal logic. The security analysis shows that the proposed method of mapping multiple watermarks into a single one overcomes the problem of volume limitation and overlapping of multiple watermarks in a multi-digital-watermarking system.

Lung cancer is one of the most life-threatening diseases in the world. The early manifestation of lung cancer is pulmonary nodules; Computed Tomography(CT) examination is the most commonly used method for early screening of pulmonary nodules. With the continuous development of computer technology, computer-aided diagnosis (CAD) system is gradually applied in the intelligent diagnosis and pre-diagnosis of pulmonary nodules and automatically analyzes medical images for different clinical diagnostic purposes. The application of computer-aided diagnosis technology based on deep learning to CT images of pulmonary nodules mainly includes five stages: data preprocessing, lung parenchyma segmentation, pulmonary nodule detection, pulmonary nodule segmentation, and benign and malignant classification. This paper conducts a comprehensive review of deep learning-assisted decision support for pulmonary nodule diagnosis, including the analysis of data set characteristics and the induction, summary, and comparison of indicators of different model algorithms on various data sets. Computer-aided diagnosis technology has laid a certain foundation for the research on intelligent diagnosis and prognosis of pulmonary nodules.