Investigating the Use of Large Language Models for Generating Abuser Stories for Early Security Threat Identification

This repository contains the complete dataset, experimental inputs, raw outputs, and validation artifacts for the study assessing the effectiveness of Large Language Models (LLMs) in generating abuser stories from user stories. The study evaluated three models (GPT-4o mini, Claude 3.5 Haiku, Gemini 1.5 Flash) using two prompting techniques (Zero-Shot and One-Shot) across 10 real-world user stories.本仓库包含了一项研究的完整数据集、实验输入数据、原始输出结果以及验证工件，该研究旨在评估大语言模型（Large Language Models, LLMs）从用户故事中生成施暴者叙事的有效性。 该研究基于10个真实世界的用户故事，采用零样本（Zero-Shot）与单样本（One-Shot）两种提示策略，对三款模型（GPT-4o mini、Claude 3.5 Haiku、Gemini 1.5 Flash）开展了评估。