An Effective Intrusion Detection System for Securing IoT Using Feature Selection and Deep Learning
G. Parimala, R. Kayalvizhi
Abstract
The Internet of Things (IoT) is playing major role in the internet world to provide the fast and smart services for the society. The IoT and the relevant devices need to be protected for ensuring the security. Here, the security is necessary today for providing secured communication services in IoT. Even though, the security in IoT is a challenging task due to the presence of various devices and sensors. To provide the security in IoT, this paper proposes a new intrusion detection system for providing secured communication in wireless environment. In this paper, we propose a new feature selection algorithm which combines the Conditional Random Field (CRF) and spider monkey optimization (SMO) for identifying the most useful features from the dataset. Here, the CRF is applied for selecting the contributed features initially. Then, the SMO is applied for finalizing the useful features from the reduced features dataset. Moreover, the CNN is used for classifying the dataset as normal and the attacks. Experiments have been conducted for evaluating the proposed IDS and proved as better in terms of detection accuracy, time and false positive rate.