<p>Cybercrime presents an escalating threat, necessitating innovative solutions beyond conventional security measures. Traditional approaches often fall short in addressing the complex and evolving nature of cyber threats. This paper proposes a novel methodology that integrates Artificial Intelligence (AI) and fuzzy logic for cybersecurity requirement engineering, specifically focused on modeling and prioritizing the requirements of the ChatGPT system. A fuzzy TOPSIS-based framework was developed, enabling stakeholders to express preferences using linguistic variables, which were then transformed into Triangular Fuzzy Numbers (TFNs) for structured evaluation. The functional and non-functional requirements were elicited using a goal-oriented strategy and modeled through use-case and class diagrams. The purpose of this study is to address the inherent ambiguity and subjectivity in stakeholder inputs by employing fuzzy logic, thus enhancing the accuracy and adaptability of requirement modeling in cybersecurity systems. A software application was also developed using VC +  + to automate the ranking process. The findings demonstrate that the proposed fuzzy-based approach effectively captures stakeholder preferences and supports the prioritization of critical requirements. The use of fuzzy TOPSIS allows for clear differentiation among requirements based on multiple evaluation criteria. These findings are significant as they provide a practical and scalable solution for requirement modeling in cybersecurity applications, facilitating better decision-making, improving system resilience, and promoting proactive threat management in AI-integrated systems like ChatGPT.</p>