Preserving sensitive data with deep learning assisted sanitisation process

Abstract

ABSTRACT This work introduces a novel privacy preservation scheme. In large databases, the data sanitisation process preserves the stored sensitive data safely from unauthorised access and users by hiding it. Moreover, the statistical features are extracted. Further, the normalised data and features are processed under the data sanitisation process. For the sanitisation process, the optimal key is produced by utilising the Deep Belief Network (DBN) with Chaotic Map-adopted Poor and Rich Optimisation (CMPRO) model. It is the modified version of the classical PRO algorithm. As a novelty, chaotic map and cycle crossover operation is included in the CMPRO algorithm. Privacy, modification degree, data preservation ratio, and hiding failure are considered as the objectives for the key generation process. Then, the data restoration process restores or recovers the sanitised data, and it is the reverse process. Then, the outcomes of the adopted scheme are analysed over the traditional systems based on certain measures. Especially, the sanitisation effectiveness of the proposed approach for data 1 in test case 2 and it is 54.56%, 51.82%, 47.94%, 49.59%, 18.17%, 43.32%, 47.03%, 47.03%, 55.79%, 21.84%, 47.33%, and 32.13% better than the existing CNN+CMPRO, RNN+CMPRO, LSTM+CMPRO, BiLSTM+CMPRO, DBN+PRO, DBN+SSA, DBN+SMO, DBN+LA, DBN+SSO, DBN+J-SSO, DBN+BS-WOA, and DBN+R-GDA schemes.