ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningNetwork SecurityAnomaly DetectionComputer IntrusionIntrusion AnalysisIntrusion DetectionRepresentation LearningThreat DetectionAttentionFeature FusionImbalanceNetwork Intrusion DetectionNetwork-based Intrusion DetectionSpatial Feature FusionTemporal FusionTemporal-spatial Feature Engineering
Network intrusion detection plays a crucial role in ensuring network security by distinguishing malicious attacks from normal network traffic. However, imbalanced data affects the performance of intrusion detection system. This paper utilizes few-shot learning to solve the data imbalance problem caused by insufficient samples in network intrusion detection, and proposes a few-shot intrusion detection method based on prototypical capsule network with the attention mechanism. Our method is mainly divided into two parts, a temporal-spatial feature fusion method using capsules for feature extraction and a prototypical network classification method with attention and vote mechanisms. The experimental results demonstrate that our proposed model outperforms state-of-the-art methods on imbalanced datasets.
29
Haibo He, Edwardo A. Garcia · IEEE Transactions on Knowledge and Data Engineering · 2009 · 9.7K citations
Generalizing from a Few Examples: A Survey on Few-Shot Learning
Yaqing Wang, Quanming Yao, James T. Kwok et al. · arXiv (Cornell University) · 2019 · 802 citations · Full text
Issues and future directions in traffic classification
Alberto Dainotti, Antonio Pescapè · IEEE Network · 2012 · 621 citations
Strategies for learning in class imbalance problems
R. Barandela, J. Salvador Sánchez, Estellito Rangel · Pattern Recognition · 2003 · 578 citations
Computing, Mathematics, Data Mining +11