Detecting Generic Network Intrusion Attacks using Tree-based Machine Learning Methods

The development Intrusion Detection System (IDS) has a solid impact in mitigating against internal and external cyber threats among other cybersecurity methods. The machine learning-based method for IDS has proven to be an effective approach to detecting either anomaly or multiple classes of intrusion. For the detection of various types of intrusion by a single IDS model, it is discovered that the overall high accuracy of the IDS model does not translate to high accuracy for each attack type. Some intrusion attacks are seen to share similarities with other attacks thereby evading detection, one of which is the generic attack. The notoriety of the generic attack is the ability of a single generic attack to compromise a whole bunch of block-ciphers. Therefore, this study proposed a machine learning framework to specifically detect generic network intrusion by implementing two (2) decision tree algorithms. The decision tree methods were developed using two distinct variants namely the J48 and Random Tree algorithms. A balanced generic network dataset was curated and used for model development. A 10-fold cross-validation technique was implemented for model development and performance evaluation, where all obtainable performance scores were extracted and presented. The performances of the decision tree methods for generic network intrusion attack detection were comparative analysis and also evaluated against existing methods. The proposed methods of this study are robust, stable and empirically seen to have outperformed existing methods.