This document describes a research paper that proposes a new intrusion detection system called HAST-IDS. HAST-IDS uses deep learning techniques to automatically learn hierarchical spatial-temporal features from network traffic data, without requiring manual feature engineering. It first uses convolutional neural networks to learn low-level spatial features, and then uses long short-term memory networks to learn high-level temporal features based on the spatial features. The system was evaluated on standard intrusion detection datasets and was shown to outperform other approaches in terms of accuracy, detection rate, and false alarm rate, demonstrating its effectiveness at feature learning and false alarm reduction.

HAST-IDS: Learning Hierarchical Spatial-Temporal Features Using Deep Neural Networks To Improve Intrusion Detection PDF

The list of books you might like