While encryption ensures the confidentiality and integrity of user data, more and more attackers try to hide attack behaviours through encryption, which brings new challenges to malicious traffic identification. How to effectively detect encrypted malicious traffic without decrypting traffic and protecting user privacy has become an urgent problem to be solved. Most of the current research only uses a single CNN, RNN, and SAE network to detect encrypted malicious traffic, which does not consider the forward and backward correlation between data packets, so it is difficult to effectively identify malicious features in encrypted traffic. This study proposes an approach that combines spatial-temporal feature with dual-attention mechanism, which is called TLARNN. Specifically, first we use 1D-CNN and BiGRU to extract spatial features in encrypted traffic packets and temporal features between encrypted streams, respectively, which enriches the features of different dimensions, and then, the soft attention mechanism is focused on the encrypted data packets to extract features. Ultimately, the second layer of the soft attention mechanism is used for aggregating malicious features. Several comparative experiments are designed to prove the effectiveness of the proposed scheme. The experimental results demonstrate that the proposed scheme has a significant performance improvement compared to existing ones.

The Energy Internet is a leading development direction for the modernized and intelligent transformation of the power grid, and a new type of infrastructure that supports the high-quality development of the economy and society. With the access of a variety of mobile terminals, security is one of the most important challenges faced in the construction of Energy Internet. Research on reliable networking and data forwarding strategies on the edge is of great significance to its development. On the basis of analyzing the requirements of typical application scenarios, we introduce in this paper a secure data transmission algorithm based on confidence of wireless opportunistic networks for Energy Internet to resist the influence of malicious behaviours. The simulations of real scenes confirm the advantages of introducing our algorithm on parameters such as the success rate and the delay of data transmission.

No abstract

No abstract

In recent years, international industrial control network security incidents have occurred frequently. As a core component of the industrial control field, intelligent power control systems are increasingly threatened by external network attacks. Based on the current research status of power industrial control network security, closely combining the development of active monitoring and defense technology in the public network field and the problems encountered by network security operators in actual work, this paper uses data mining methods to study the power control system network security situation awareness technology. Combing operational data collection and integrated processing, situation index screening and extraction, we use wavelet neural network analysis method to train the sampled data set, and finally calculate the true value of the network security status through deep intelligent learning. Finally, we conclude that the artificial intelligence algorithm based on wavelet neural network can be used for power control system network security situation awareness. In actual work, it can predict the situation value for a period of time in the future and assist network security personnel in judgment and decision-making.