2020 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS) · 2020 · 17 citations · 33 references
ComputingComputer ScienceCybersecurityComputer SecurityFeature EngineeringMachine LearningDeep LearningFeature SelectionIntrusion DetectionRepresentation LearningDeep Learning-based Anomaly DetectionDeep Learning-based DetectionFeature Selection For Intrusion DetectionMachine Learning For Intrusion DetectionNeural Network ModelingNormalizationScore Normalization
To stay ahead of novel attacks, cyber security professionals are developing new software and systems using machine learning techniques. Neural network architectures improve such systems, e.g., IDS, by implementing anomaly detection, which differentiates benign packets from malicious packets. In order for an IDS to best predict anomalies, the data the model is trained on is typically pre-processed through normalization and feature selection/reduction. The impacts of pre-processing techniques play an important role in training a neural network to optimize its performance. This paper proposes a DNN with 2 hidden layers for the IDS architecture and compares two commonly used normalization pre-processing techniques. We find that using Z Score normalization increased performance in accuracy by 4.46% reduced loss by 2.04%, improved F-Score by 4.70%, and increased AUC-ROC by 23.64%.
33
A detailed analysis of the KDD CUP 99 data set
Mahbod Tavallaee, Ebrahim Bagheri, Wei Lu et al. · 2009 · 4.8K citations · Full text
A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks
Chuanlong Yin, Yuefei Zhu, Jinlong Fei et al. · IEEE Access · 2017 · 2K citations · Full text
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
Testing Intrusion detection systems
John McHugh · ACM Transactions on Information and System Security · 2000 · 1.3K citations · Full text