Information Security Situation Awareness Based on Big Data Technology
Chuang Ma · 2024
With the increase in the number of network nodes, inadequate network security protection, and untimely repair of security patches, various vulnerabilities in the network are gradually being exploited by attackers. With the help of big data (BD) technology, massive data such as network traffic, user behavior, and threat intelligence can be deeply mined and correlated for timely detection of security threats. This article proposes a deep learning based situational awareness and assessment model. This model utilizes the powerful feature extraction and pattern learning capabilities of deep learning to extract key information from network traffic, system logs, and other data, and accurately identify network security threats. Through experimental comparison with decision tree algorithm and random forest algorithm, this model has achieved significant advantages in both recall and accuracy, with a recall of 88.7% and an accuracy rate of 93.8%. These results indicate that the proposed model can more comprehensively identify security threats and provide more accurate security decision-making basis. The research results provide an effective method for network security situational awareness (NSSA) and demonstrate the potential of deep learning based data mining (DM) technology in the field of network security.