Nature inspired computational intelligence implementation for privacy preservation in MapReduce framework

Abstract

The next generation technologies made huge impact on the extent of data usage and motivated researches in data-management field along-with the advances in the automation in machine-human interactions. Cloud data storage plays significant role in handling big data. However, data security and data privacy-preservation are still very challenging issues. Several techniques are developed to do privacy preservation keeping in mind the data utility and data obfuscation; however, the trade-off among the privacy of data and its utility is not properly tackled. To solve many optimisation problems, the current trend is use of nature-inspired optimisation algorithms. This paper proposes implementation of two nature inspired optimisation algorithms; cat swarm optimisation and grey wolf optimiser; along with adaptation of k-anonymisation criteria in the MapReduce framework for achieving privacy preservation goal. A fitness function is defined that maintains trade-off between privacy and utility of information given to end-user. Comparative analysis of proposed technique with established techniques is done on parameters: classification accuracy and information loss.