Hashed Needham Schroeder Industrial IoT based Cost Optimized Deep Secured data transmission in cloud

Abstract

Deep learning is an encouraging approach for extracting precise information from raw sensor data from IoT devices. In this paper, Hashed Needham Schroeder (HNS) Cost Optimized Deep Machine Learning (HNS-CODML) method for secure Industrial IoT data transmissions via cloud environment has been proposed by indicating the necessity of providing Industrial IoT security using machine learning technique. First, HNS Public Key Generation (PKG) mechanism computes the public key and a flag value, then using public key, the execution time has been improved as only authenticated cloud users (CU) are allowed to exchange the data/messages via secured channel and can be trained; thus the cost function can be computed using two passes. In the first pass, the cost function has been measured while in second pass, the overall cost function is obtained, therefore reducing the computational cost (CC) and communication overhead (CO), making the entire process much easier to monitor and control.