A2S-AFLNet: An Adaptive Bat Optimized Two-Stage Attention Fused LSTM Networks for Attack-Resilient Intrusion Detection

Abstract

With the increasing sophistication of cyber security risks, utilizing machine learning algorithms alongside intrusion detection systems has become crucial. Conventional approaches to detection intrusion on network traffic data come with limitations such as higher false positive rates, inability to adapt evolving attack patterns, and ineffective handling of large data volume. Deep neural networks such as long short-term memory (LSTMs) are good at understanding patterns in network data over time. Sometimes, they overlook aspects that can cause unnecessary calculations, which leads to less optimal detection results. We present an adaptive bat-optimized and two-stage LSTM network fused with attention (A2S-AFLNet) to address these issues. This method combines attention mechanisms and LSTM to improve feature selection while also making the learning process more efficient and adaptable for intrusion detection. Standard performance metrics were analyzed and compared with the recent machine learning and neural network-based IDS models using the UNSW-NB15 dataset to validate the robustness of the framework.