Hybrid Optimization Techniques for Data Privacy Preserving in the Metaverse Ecosystem
M. P. Karthikeyan, K.S. Krishnaveni, T. Revathi, A. Hema Ambiha · Advances in computational intelligence and robotics book series · 2023
Large-scale electronic databases are being maintained by businesses and can be accessed via the internet or intranet. Employing data mining techniques, significant information was extracted from the data. The privacy of the data is inherently at risk while data mining operations are being carried out. All users shouldn't have access to the private information stored in the database. Methods for protecting privacy have been suggested in the literature. Algorithms used in privacy-preserving data mining (PPDM) on private data are unknown even to the algorithm operator. Personal information about users and data on their collective behaviour are the two main aspects of privacy preservation. The majority of privacy-preserving techniques rely on reducing the level of granularity used to represent the data. Although privacy is improved, information is lost as a result. As a result, with PPDM, there is a trade-off between privacy and information loss. Effective methods that don't undermine the security defences are needed.