A Hybrid Cloud Intrusion Detection Method Based on SDAE and SVM
Wenjuan Wang, Xuehui Du, Dibin Shan, Na Wang · 2019
Network intrusion detection is one of the effective methods to prevent the cloud environment from malicious attacks. In this paper, we propose a cloud intrusion detection method based on stacked denoising autoencoders (SDAE) and support vector machine (SVM). Utilizing the unsupervised deep learning algorithm SDAE for dimensionality reduction, and using the supervised shallow learning algorithm SVM for building classifier to detect malicious attacks. The detection performance of the proposed SDAE+SVM model has been evaluated using the well-known intrusion detection evaluation datasets namely the NSL-KDD.