Cyber Risk Recommendation System for Digital Education Management Platforms.

Area of Science:

• Cybersecurity
• Educational Technology
• Artificial Intelligence

Background:

• The COVID-19 pandemic necessitated a rapid shift to distance learning, increasing cybersecurity risks for students.
• Younger learners are particularly vulnerable to cyber fraud due to a lack of adequate training and information.
• E-learning platforms face threats like malware, phishing, and malicious remote access, jeopardizing learner data.

Purpose of the Study:

• To develop an innovative cyber risk recommendation system for digital education management platforms.
• To address the heightened cybersecurity challenges in e-learning environments.
• To protect learners and their data from online threats during remote education.

Main Methods:

• A distributed, two-stage algorithm combining game theory and machine learning.
• User-driven training of the algorithm based on security-maximizing recommendation choices.
• Simulation of a user system analyzing independent choices and environmental influences within a cyber-physical-social framework.

Main Results:

• The proposed algorithm effectively simulates user behavior in a digital learning environment.
• The system demonstrates flexibility and efficiency in adapting to user choices and environmental factors.
• The algorithm successfully assesses and mitigates cyber risks in e-learning.

Conclusions:

• The developed cyber risk recommendation system is effective for protecting e-learning education.
• The system offers a flexible and efficient approach to risk assessment in digital learning.
• This innovative solution enhances the security of educational technology platforms.