Privacy and security of big data in cyber physical systems using Weibull distribution-based intrusion detection

Abstract

The volume of data collected from cyber physical systems (CPS) is huge, and we use big data techniques to manage and store the data. Big data in CPS is concerned with the massive heterogeneous data streams, which are acquired from autonomous sources and computed in distributed data storage system. In order to handle the size, complexity and rate of availability of data, it requires new techniques that can inspect and interpret useful knowledge from large streams of information, which impose challenges on the design and management of CPS in multiple aspects such as performance, energy efficiency, security, privacy, reliability, sustainability, fault tolerance, scalability and flexibility. This paper focuses on the security and privacy aspects in managing big data for CPS and reviews recent challenges in data privacy. We also present a protection framework for intrusion detection and analyze the performance parameters, reliability and failure rate in a malicious big data context.