A Conceptual Anonymity Model to Ensure Privacy for Sensitive Network Data

Abstract

In today’s world, a great amount of people, devices, and sensors are well connected through various online platforms, and the interactions between these entities produce massive amounts of useful information. This process of data production and sharing appears to be on the rise. The growing popularity of this industry, as well as the required development of data sharing tools and technology, pose major threats to an individual’s sensitive information privacy. These privacy-related issues may elicit a regularly strong negative reaction and restrain further organizational invention. Researchers have identified the privacy implications of large data collections and contributed to the preservation of data from unauthorised exposure to solve the challenge of information privacy. However, the majority of privacy strategies concentrate solely on traditional data models, such as micro-data. The academe and industry are paying more attention to network data privacy challenges. In this paper, we offer (ℓ, k)-anonymity, a novel privacy paradigm for network data that focuses on maintaining the privacy of both node and link information. Here, original network data will turn to attribute generalization nodes through a complex process, where several algorithms, clustering, node generalization, link generalization and ℓ-diversification will be applied. As a result, (ℓ, k)-anonymous network will be generated and will filter original network data to ensure publishable (ℓ, k)-anonymize data. Hopefully, this anonymity model will have a stronger role against homogeneity attacks of intruders, which will prevent the unauthorized disclosure of sensitive network data for several areas, such as - health sector. This model will also be cost effective and data loss will be controlled using two different ways.