TL;DR采用堆叠自编码器(SAE)和长短期记忆(LSTM)方案,通过特征选择和零日威胁分类,实现对零日攻击的检测和分类,结果表明 SAE-LSTM 模型具有较高的准确性、召回率和 F1 分数,能够有效识别各种类型的零日攻击。
Abstract
zero-day attack detection plays a critical role in mitigating risks,
protecting assets, and staying ahead in the evolving threat landscape. This
study explores the application of stacked autoencoder (SAE), a type