A Deep Learning-Based Intrusion Detection System using Refined LSTM for DoS Attack Detection
Mohammad O. Hiari, Yousef Alraba’nah, Iyas Qaddara
Abstract
The detection of a Denial of Service (DoS) attacks is a key challenge in network security, directly impacting the availability and reliability of networks. Such attacks have to be mitigated by implementing an accurate and timely detection mechanism to ensure the integrity of the network infrastructure. Driven by the shortcomings of conventional attack detection methods and the growing complexity of the network attacks, this work proposes a new customized Long Short-Term Memory (LSTM) model for DoS attacks detection. The proposed deep learning approach utilizes LSTM's strength in learning long-range dependencies in sequential data to model network traffic patterns over time. The effectiveness of the model is evaluated through comparative experiments. The primary outcome is that the proposed LSTM model has improved detection performance across all metrics of precision, recall, F1-score, and accuracy. The results demonstrate that the proposed LSTM architecture is a promising and trustworthy solution for enhancing intrusion detection systems (IDSs) and protecting network systems against DoS attacks.