Research on the Security Assessment of Communication Data in Higher Vocational Education Management Platforms Based on Statistical Methods

This study develops a statistical framework to assess the security of communication data in higher vocational education management platforms (HVE-MPs), providing quantitative risk evaluation and anomaly detection across large-scale datasets. Methods including logistic regression, ARIMA-based time series analysis, Z-score and Grubbs’ test anomaly detection, and cumulative sum (CUSUM) control charts are applied to over one million communication logs to identify high-risk channels and predict breach probability. The approach highlights key operational risk factors, such as peak usage periods and concentrated attack patterns, and enables proactive, data-driven mitigation strategies. The framework is particularly relevant for communication-intensive environments, including wireless networks and antenna-supported information transmission systems, where secure and reliable data exchange is critical. Experimental results demonstrate high anomaly detection accuracy (>95%), low false alarm rates, and effective identification of the top 5% of high-risk channels, supporting continuous security monitoring and adaptive defense strategies in complex digital platforms.