Detecting Security and Privacy Attacks in IoT Network using Deep Learning Algorithms

Abstract

The Internet of Things (IoT) is the 21st century’s fastest-growing technology. Nearly by the end of 2025, 75 billion IoT devices will be get connected to the internet. As a result, safeguarding devices from attacks and maintaining user privacy-related data has become extremely difficult. In this paper, we propose an efficient model to detect security and privacy related threats in IoT environment using different machine learning and deep learning algorithms on open-source standard dataset like NSL-KDD (Knowledge Discovery Data) and UNSW-NB15, which were made accessible for conducting research activities purposes. Here we analyzed the feature set of the data required to detect various threats mentioned in the given dataset using proposed model. This paper examines the binary and multiclass attacks classification using neural network and machine learning approaches. RNN model outperformed with higher accuracy in detecting threats with 99.4 percent for binary classification and 96.2 percent for multiclass classification.