Use of Machine Learning in Interactive Cybersecurity and Network Education.

Area of Science:

• Computer Science
• Cybersecurity Education

Background:

• Cybersecurity education presents challenges for students, with existing online tools often lacking constructive feedback or oversimplifying content.
• Hands-on labs and simulations are crucial for effective cybersecurity learning, but current platforms have limitations.

Purpose of the Study:

• To develop an advanced cybersecurity education platform offering both user interface and command-line access.
• To implement an auto-constructive feedback mechanism for command-line practices using machine learning.
• To provide customizable exercises and progressive difficulty levels for enhanced learning.

Main Methods:

• Development of a cybersecurity education platform with nine progressive levels and a customizable network testing environment.
• Integration of a machine learning model for automatic detection and correction of typographical errors in command-line practice.
• Conducting a user trial with pre- and post-usage surveys to assess the impact of auto-feedback.

Main Results:

• The platform features a user interface and command-line options with increasing difficulty levels.
• An automated feedback system utilizing machine learning identifies and corrects user typographical errors.
• User trials indicated a significant net increase in positive ratings across various aspects, including user-friendliness and overall experience.

Conclusions:

• The developed platform effectively supports cybersecurity education through interactive labs and auto-feedback.
• Machine learning-based feedback significantly improves user-friendliness and overall engagement in cybersecurity learning.
• The platform offers a valuable tool for enhancing practical cybersecurity skills and knowledge acquisition.