A hybrid unsupervised clustering-based anomaly detection method

In recent years, machine learning-based cyber intrusion detection methods have gained increasing popularity. The number and complexity of new attacks continue to rise; therefore, effective intelligent solutions are necessary. Unsupervised learning techniques particularly appealing systems since they can detect known unknown types as well zero-day attacks. the current paper, we present an unsupervised anomaly method, which combines Sub-Space Clustering (SSC) One Class Support Vector Machine (OCSVM) without any prior knowledge. proposed approach is evaluated using well-known NSL-KDD dataset. experimental results demonstrate that our method performs better than some existing techniques.