Author : Miss.Deepika R.Pede and Dr.Vaishali P.Vikhe

Network based communication is more vulnerable to outsider and insider attacks in recent days due to its widespread applications in many fields. Intrusion Detection System (IDS) a software application or hardware is a security mechanism that can monitor network traffic and find abnormal activities in the network. As attackers always change their techniques of attack and find alternative attack methods, IDS must also evolve in response by adopting more sophisticated methods of detection.The huge growth in the data and the significant advances in computer hardware technologies resulted in the new studies existence in the deep learning field, including intrusion detection. Deep learning (DL) is a subset of Machine Learning (ML) that is based on learning data representations. This paper proposes a novel deep learning model to enable IDS operation within modern networks. The model shows a combination of deep learning and machine learning, capable of correctly analyzing a wide range of network traffic. The novel approach proposes non-symmetric deep autoencoder (NDAE) for unsupervised feature learning. Moreover,it additionally proposes a novel classification model built utilizing stacked NDAEs.The performance is evaluated using a network intrusion detection analysis dataset, particularly the WSN Trace dataset. The contribution work is to implement advanced deep learning algorithm contains IDS functionality but more sophisticated systems which are capable of taking immediate action to prevent or reduce the malicious behavior.

Keywords: Intrusion Detection System (IDS), NonSymmetric Deep Auto-Encoder (NDAE), Deep Learning (DL), WSN, Machine Learning (ML).