While cyber physics system (CPS) provides forward-looking and personalized services for users, it also creates conditions for the spread of malware. Therefore, it's critical for us to analyse affecting factors and study the propagation characteristics of malware. On the basis of the difference of intelligent device's dissemination capacity and discriminant ability, a dynamic malware propagation model (Disseminate&Discriminate-Spread-Exposed-Ignorant-Recover, DDSEIR) is proposed. First, intelligent devices are classified into different groups according to the level of dissemination capability by hierarchical mechanism, which takes the networks topology into account. And subsequently, intelligent device's discriminant ability can be evaluated by sender's identity and information attributes. Then, the mean field equation is constructed to analyze the dynamic characteristics of DDSEIR and the factors that influence malware propagation, which is used to further derive the malware propagation scale and threshold value of diffusion. Finally, this paper uses Live Journal dataset to verify the effectiveness of DDSEIR. The experiments illustrate that intelligent device's dissemination capacity and discriminant ability have significant influences on malware propagation.
The intrusion detection schemes (IDSs) based on the Gradient Boosting Decision Tree (GBDT) face three problems: unbalanced training data distribution, large dimensionality of data features, and difficulty in model parameter optimization, which lead to weak monitoring capability and high false positive rate. For the problem of unbalanced training data distribution, we make the one-sided gradient oversampling algorithm to ensure the balance between the data of each category. To tackle the problem of the large dimensionality of data features, we develop a hierarchical cross-validation algorithm for binding mutually exclusive features. To address the problem of difficulty in model parameter optimization, we design a Bayesian optimization algorithm to make the model parameter search process more targeted and reduce the model training cost by establishing functional relationships between hyperparameters and target functions. The detailed experimental results show that the scheme can effectively solve the problems of data imbalance, high-dimensional data features, and low parameter finding efficiency, and improve the model’s ability to monitor the attack behavior.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.