Cognitive Differences in Network Security Based on Mathematical Modeling Based on Ensemble Learning Algorithm

With the rapid development of network technology and digital economy, network security issues are increasingly receiving widespread attention. People’s awareness of network security has attracted the attention of many scholars. This study obtained a large amount of relevant data through questionnaire surveys and practical task tests, and conducted in-depth analysis of the original data using ensemble learning algorithms, including feature extraction, model training, result prediction, and other steps. This study chose random forest as the ensemble learning algorithm because it has high training speed, good parallel computing ability, good scalability, and efficient memory management in mathematical modeling. In addition, this study also designed mathematical modeling tasks, including illegal access behavior in network intrusion, and trained a classification model using random forest algorithm. Finally, the performance of the model was comprehensively evaluated by dividing the data into 10 test sets and conducting independent performance tests. Research has found significant differences in the cognitive aspects of mathematical modeling of cybersecurity among different groups, mainly reflected in their understanding of cybersecurity issues, selection of response strategies, and risk assessment. In addition, the study also found that factors such as educational background, work experience, and cybersecurity awareness have a 30%, 36%, and 21% impact on people’s cognitive performance, respectively. Among them, educational background and work experience determine people’s understanding and response ability to network security issues, while network security awareness directly affects people’s level of attention to network security issues and willingness to take preventive measures