Automated Screen Protection System Against Wi-Fi-Based Threats

Wireless communication technologies have significantly improved connectivity, collaboration, and remote accessibility. However, the rapid adoption of Wi-Fi networks and remote screen-sharing applications has introduced severe security vulnerabilities simultaneously. Unauthorized screen monitoring, covert remote desktop access, and data exfiltration over wireless networks have become increasingly prevalent, especially in environments where users unknowingly grant permissions to remote tools or where legitimate applications are exploited maliciously. Traditional security mechanisms, such as signature-based antivirus systems and static firewall configurations, are insufficient to detect behavioral anomalies or misuse of trusted remote access applications. These approaches focus primarily on known malware patterns and predefined rule sets, which fail to identify abnormal upload behavior, sustained data transmission activities characteristic of screen-sharing attacks. To address these limitations, this research proposes a real-time Automated Screen Protection System specifically designed to detect and mitigate Wi-Fi-based screen monitoring threats in Windows environments. The system integrates continuous network traffic monitoring, statistical anomaly detection using Z-score modeling, upload dominance ratio analysis, process-level network inspection, and a weighted multi-factor risk scoring framework. Unlike conventional monitoring systems, the proposed architecture does not rely solely on threshold violations but instead correlates multiple behavioral indicators to reduce false positives. Upon detection of sustained suspicious activity exceeding a predefined risk threshold, the system autonomously executes defensive countermeasures, including termination of suspicious processes, disabling of Wi-Fi connectivity, user alert notification, and system lock enforcement. Experimental validation demonstrates enhanced detection accuracy, reduced false alarms, and rapid response latency compared to simple threshold-based detection mechanisms. The proposed framework provides an intelligent, autonomous, and practical endpoint protection mechanism against modern Wi-Fi-based threats.