IEEE Access · 2024 · 18 citations · 30 references
ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningNetwork SecurityAnomaly DetectionAttention NetworksDeep LearningIntrusion DetectionPattern RecognitionRepresentation LearningAttentionBinary ClassificationDeep Learning For Intrusion DetectionDeep Learning-based DetectionMachine Learning For Intrusion DetectionNetwork Intrusion DetectionNetwork-based Intrusion DetectionPrecision
The goal of current research will be to increase the accuracy and generalisation capacity of intrusion detection models in order to better handle the complex network security issues of today. In this paper, a new hybrid attention mechanism is introduced along with an enhanced algorithm. Through the effective channel layer and curve space layer, the feature information will be concentrated on the necessary feature information, allowing the model to concentrate more on the features linked to classification and become more broadly applicable. Increase the model’s precision. The experimental results demonstrated that the accuracy can achieve 100%, 99.79%, and 98.10% on binary classification problems and 96.37%, 98.12%, and 99.06% on multiclassification problems, respectively, using the UNSW-NB15, CICIDS-2017, and CICIDS-2018 datasets for validation.
30
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Qilong Wang, Banggu Wu, Pengfei Zhu et al. · 2020 · 8.1K citations
Deep Learning Approach for Intelligent Intrusion Detection System
R. Vinayakumar, Mamoun Alazab, K. P. Soman et al. · IEEE Access · 2019 · 1.8K citations · Full text
Network Intrusion Detection Combined Hybrid Sampling With Deep Hierarchical Network
Kaiyuan Jiang, Wenya Wang, Aili Wang et al. · IEEE Access · 2020 · 438 citations · Full text