Methodology for Detecting Cyber Intrusions in e-Learning Systems during COVID-19 Pandemic.

Area of Science:

• Cybersecurity
• Computer Networks
• Educational Technology

Background:

• The COVID-19 pandemic highlighted the critical reliance on e-learning systems.
• Distributed Denial of Service (DDoS) attacks pose a significant threat to e-learning infrastructure, disrupting educational continuity.
• Botnets, particularly those leveraging Internet of Things (IoT) devices, are key enablers of large-scale DDoS attacks.

Purpose of the Study:

• To analyze the impact of the COVID-19 pandemic on e-learning systems in Croatia.
• To propose a research methodology for developing a cyber-threat detection model for e-learning environments.
• To differentiate malicious DDoS attacks from legitimate flash crowd events in e-learning network traffic.

Main Methods:

• Literature review on network anomalies and DDoS attack mechanisms.
• Establishment of a theoretical framework for DDoS and flash crowd traffic analysis.
• Development and testing of a DDoS detection model using a laboratory testbed and real-world case study data.

Main Results:

• Identification of network anomalies, specifically DDoS attacks, as critical threats to e-learning systems.
• Analysis of the impact of the COVID-19 pandemic on Croatian e-learning platforms.
• Proposed methodology for a cyber-threat detection model tailored for e-learning systems during crises.

Conclusions:

• Timely detection of DDoS attacks can significantly improve the quality and reliability of the e-learning process.
• The developed methodology contributes to a specialized research domain in cybersecurity for e-learning.
• Implementation of the model enhances the cybersecurity posture of e-learning systems and provides valuable datasets for future research.