Network Data Security for the Detection System in the Internet of Things with Deep Learning Approach

We thought to set up a system of interconnection which allows sharing the communication network of data without the intervention of a human being. The Internet of Things system allows many devices to be connected for a long time without human intervention, data storage is low and the level of data processing is reduced, which was not the case with older solutions proposed to secure the data for example: cyber-attack and other systems. But other theories like for example: artificial intelligence, machine learning and deep learning have a lot to show their ability and the real values of heterogeneous data processing of different sizes and many researchers had to work on it.In the case of our work, we have used deep learning theories, to achieve a light data interconnection security solution; we also have TCP/IP protocol for data transmission control, algorithm drillers for classifications. In order to arrive at a good solution; First, we thought of a model for anomalies detection in Internet of Things and we think about the improvement of architectures of the Internet of the existing objects already proposed a system with a light solution and especially multilayer for an IoT network. Second, we analyzed existing applications of machine learning, deep learning to IoT, and cybersecurity. The recent hack of 2014 Jeep Cherokee, iStan pacemaker, and a German steel plant are a few notable security breaches. Finally, from the evaluated metrics, we have proposed the best neural network design suitable for the IoT Intrusion Detection System. With an accuracy of 98.91% and False Alarm Rate of 0.76 %, this research outperformed the performance results of existing methods over the KDD Cup '99 dataset. For this first time in the IoT research, the concepts of Gated Recurrent Neural Networks are applied for the IoT security.