ChatGPT vs. Gemini: Comparative Evaluation in Cybersecurity Education with Prompt Engineering Impact

The advent of Large Language Models (LLMs) has revolutionized numerous domains, notably education, by offering powerful tools for personalized learning and automated assistance. These models have the potential to significantly enhance the educational experience, particularly in the field of Computer Science (CS), where the complexity and rapidly evolving nature of topics present unique challenges and opportunities. In this study, we present a comparative evaluation into the transformative potential of LLMs in CS education, with a specific focus on cybersecurity. Our study centers on two leading LLMs: Ope-nAI's ChatGPT and Google's Gemini Pro, employing a three-fold assessment methodology. Firstly, we analyze the subject matter within cybersecurity education to identify key topics and challenges for examination. Secondly, we meticulously assess and compare the efficacy of ChatGPT and Gemini across various factors in producing satisfactory responses. Lastly, we explore the impact of leveraging prompt engineering on enhancing the quality of responses generated by these AI tools. Through this holistic approach, our research aims to provide insights into the strengths, limitations, and potential avenues for enhancement of these models, thereby enriching the ongoing discourse on LLMs integration in higher education.