xgh123/phreshphish

PhreshPhish是一个用于钓鱼网页检测的大规模、真实世界数据集和基准测试，包含钓鱼和良性HTML-URL对。训练集有498,255个样本：276,729个良性样本和221,526个钓鱼样本；测试集有168,060个样本：91,260个良性样本和76,876个钓鱼样本。基准测试包含975个基准，基础率范围在[5e-4, 1e-3, 5e-3, 1e-2, 5e-2]之间。PhreshPhish is a large-scale, real-world dataset and benchmark for phishing webpage detection containing phishing and benign HTML-URL pairs. Train: 498,255 samples: 276,729 benign and 221,526 phish; Test: 168,060 samples: 91,260 benign and 76,876 phish; Benchmarks: 975 benchmarks with base rates ranging from [5e-4, 1e-3, 5e-3, 1e-2, 5e-2].