Web page phishing detection dataset

本数据集名为'Web page phishing detection dataset'，由11430个钓鱼和合法URL组成，旨在为机器学习在网站钓鱼检测中的应用提供基准数据。数据集的创建遵循了一套详细的构建指南，包括从多个来源收集URL，确保数据的多样性和代表性。数据集的构建过程包括URL的预处理、特征提取、数据平衡和随机化，以支持系统的公平评估和比较。此数据集特别适用于研究钓鱼网站的快速变化和机器学习模型的适应性，为信息安全领域的研究提供了重要的资源。

This dataset is named 'Web page phishing detection dataset', which comprises 11,430 phishing and legitimate URLs. It is designed to provide benchmark data for the application of machine learning in website phishing detection. The development of this dataset follows a detailed set of construction guidelines, which includes collecting URLs from diverse sources to ensure the data's diversity and representativeness. The dataset construction process encompasses URL preprocessing, feature extraction, data balancing, and randomization, enabling fair evaluation and comparison of related systems. This dataset is particularly applicable to research on the rapid evolution of phishing websites and the adaptability of machine learning models, serving as a valuable resource for studies in the field of information security.