Skip to main content Skip to navigation

CyberMentor: AI Powered Learning Tool Platform to Address Diverse Student Needs in Cybersecurity Education

Project Overview

The document explores the CyberMentor platform, an innovative AI-driven educational tool focused on enhancing cybersecurity education for diverse learners, particularly non-traditional students who often encounter obstacles like inadequate mentorship and resources. By leveraging Generative Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques, CyberMentor provides personalized support, tailored career guidance, and real-time assistance, aiming to improve knowledge acquisition, skill development, and career readiness. The platform's design promotes equity and accessibility, ensuring that all students can benefit from enhanced educational resources and mentorship opportunities, thereby addressing systemic challenges within the field of cybersecurity education. Ultimately, the findings highlight the effectiveness of generative AI in creating a more supportive and inclusive learning environment, facilitating better outcomes for students as they navigate their educational and professional journeys.

Key Applications

AI-Powered Cybersecurity Learning Tools

Context: These tools are designed to enhance cybersecurity education for non-traditional students, including part-time students and veterans. They support students in various aspects of cybersecurity, such as understanding cryptography, writing scripts for network anomaly detection, and developing machine learning models for threat detection.

Implementation: The AI-powered platform utilizes large language models (LLMs) and retrieval-augmented generation (RAG) to provide personalized mentoring and support. It includes various tools that guide students through complex concepts, offering structured workflows for problem-solving and hands-on experience.

Outcomes: ['Enhanced accessibility to information and resources for diverse student populations.', 'Improved student engagement through personalized mentoring and interactive learning experiences.', 'Reinforced theoretical understanding and practical skills in areas like cryptography, scripting, and machine learning.']

Challenges: ['Limited access to mentors and outdated knowledge resources.', 'Complexity of mathematical reasoning in cryptography and machine learning concepts may lead to inaccuracies or overwhelm students, especially those from non-technical backgrounds.', 'Students may struggle with the abstract nature of scripting and network concepts.']

Implementation Barriers

Access Barrier

Limited access to timely mentoring and educational resources for non-traditional students.

Proposed Solutions: Implementing a 24/7 real-time educational support system to provide continuous assistance.

Resource Barrier

Outdated knowledge resources hinder students' ability to stay current with the rapidly evolving field.

Proposed Solutions: Utilizing RAG techniques to ensure access to up-to-date, relevant educational materials.

Curriculum Barrier

Difficulty in balancing foundational knowledge and advanced concepts in cybersecurity.

Proposed Solutions: Creating a balanced and adaptive curriculum that integrates academic and industry resources.

Skill Development Barrier

Challenges in developing analytical and programming skills necessary for cybersecurity.

Proposed Solutions: Providing personalized tutoring and iterative learning frameworks to reinforce foundational skills.

Project Team

Tianyu Wang

Researcher

Nianjun Zhou

Researcher

Zhixiong Chen

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Tianyu Wang, Nianjun Zhou, Zhixiong Chen

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies