Secured Authentication and Optimal Key-Based Encryption for Data Privacy Preservation in Mobile Crowd Sensing

Abstract

Mobile crowd sensing (MCS) has key strategy for immediately monitoring situations in urban areas and connected vehicles, if the use of a devoted network of sensors is more or less feasible. By exploiting mobile devices and users of smartphones globally, MCS provides an infinite number of unique capabilities. When such a system is extremely beneficial, it requires precise data from sensing and the people who carry them (i.e., users) throughout task supervisory activities such as participant selection and work distribution. People may be hesitant to give data due to privacy concerns. To address and resolve privacy concerns, a data privacy preservation model and anomaly detection are proposed. The major intention of the model is to perform security-based dynamic authentication to achieve privacy preservation in data. Initially, for security purposes, the machine learning algorithm Weighted Probabilistic Neural Network (WPNN) is used, in which the weight optimization is done by Improved Red Panda Optimization (IRPO). Subsequently, with the help of non-attacked network, the dynamic authentication is performed using the Nash Equilibrium (game theory). In further stages, the privacy preservation of data is accomplished by Optimal Key-based Attribute-Based Encryption (OK-ABE). Lastly, the effectiveness of the system is validated and measured across diverse metrics. Therefore, the outstanding results prove that it effectively detects the anomalies and preserves the data.