ITrust: An Isolation Forest-Based Anomaly-Resilient Trust Model for Underwater Acoustic Sensor Networks

PROJECT TITLE :

ITrust: An Anomaly-Resilient Trust Model Based on Isolation Forest for Underwater Acoustic Sensor Networks

ABSTRACT:

Underwater acoustic sensor networks, also known as UASNs, have received a lot of attention as a potential tool for the development of a wide range of different types of marine applications. In these networks, the sensor nodes collaborate in order to accomplish certain goals. An associated trust model plays a significant role in node trustworthiness evaluation and defective node detection, such as in the case of adverse attacks on the network. This is because the sensor nodes are left unattended while being continuously exposed to harsh environments. However, the existing trust models only evaluate the Communication behavior and the energy of the sensor nodes. They completely ignore the effects of the underwater environmental noise on the trust reliability of the network. In addition, the vast majority of trust models are developed with arbitraty weighted trust metrics, which results in unavoidable evaluation errors. In order to arrive at an accurate calculation of node trust, we propose a brand new trust model that is resistant to anomalies and attacks and is based on the isolation forest. This model is known as ITrust by our team. The ITrust model that has been proposed has two phases: the first one deals with trust metrics specifics, and the second one identifies defective nodes. The first step involves integrating the trust dataset with four different types of trust metrics, namely Communication trust, data trust, energy trust, and environment trust. Using the trust dataset that was obtained in the previous step, the isolation forest algorithm is used in the next stage to perform a trust evaluation. The results of the simulations show that the proposed ITrust is able to effectively detect defective nodes and achieves higher detection accuracy than the existing trust models can manage in an environment with a lot of background noise.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here