An Experiment with Focus on Security Through Large- Language Models Using Behavior-Driven Development

Requirements elicitation is a fundamental activity in a software development process, which means it needs to be carried out effectively, aiming the requirements to perform the behavior expected by the software. Problem: The need for assertiveness in requirements elicitation tasks can impact subsequent activities of software development. Solution: It is proposed an experiment focusing on the security non-functional requirement expressed in the ISO/IEC 25010:2023 Standard through Large-Language Models (LLMs) using Behavior-Driven Development (BDD). Method: Via an experiment, this study is qualitative and descriptive. It is possible to analyze, through statistical tests, the effectiveness of LLMs to elicit non-functional requirements. Summarization of Results: The study presented the effectiveness of using pre-defined prompts for test automation through machine learning. Contributions and impact: Through this experiment, it is possible to present an effective collaboration between human and artificial intelligence, generating time savings for automatic generation of tests.