ADVANCED SECURE AND PRIVACY PRESERVING DATA DEDUPLICATION USING EXTREME LEARNING MACHINE

Abstract

 Data deduplication is a technique for eliminating duplicate copies of data, and has been widely used in cloud storage to reduce storage space and upload bandwidth. The centralized DeKey based deduplication system in which user do not need to handle any keys on their own but as a substitute securely distribute the convergent key across multiple servers.. The existing system is limited high overheads and may also suffer from falsified aggregated results returned by a malicious server. Wireless sensor networks (WSN) and Cloud Computing to conduct an analysis of previously published research and provide a summary of the efforts put into researching BC applications for network security. We present the research paper is developed practical privacy security analytics in information systems. Cloud Technology is providing prompt Internet access as well as feasible access to information from any location and platform at any given time. There has been a significant rise in the volume of information produced as well as the take different involved in its data type. We propose a mapping framework to employ a fine-tuned multilayer feed forward artificial neural network (ANN) and extreme learning machine (ELM) for role engineering in the SCADA-enabled IIoT environment to ensure privacy and user access rights to resources.  Our proposed system to entire application space for applying reinforcement learning to IIoT systems into four scenarios, namely, non-continuous learning without learning model sharing, non-continuous learning with learning model sharing, continuous learning without learning model sharing, and continuous learning without learning model sharing. Security analysis shows that our scheme protects the privacy of inputs, ML model and prediction results.