ABSTRACT
The IoT environment and its highly interconnected technologies are now evolving quickly. Academic study, scientific research, industry, banking & finance, business & marketing, and IoT devices and services are involving in digitation. The large amount of digital data is generated during the data publishing, sharing and transferring. Social networks play an important role in today's interconnect development like LinkedIn, Facebook, Twitter etc. The data security is crucial for maintaining privacy rights; thus, it must be safeguarded against unauthorized access and dissemination. There are several cryptographic techniques and different privacy strategies involved in protection, however “Data anonymization” is just another option or a straightforward strategy. According to literature work there are many data anonymity tools on data security, presently all of anonymity tools using the concept of Differential Privacy (DP). It adds the noise by using the Approximate differentiation with Laplace distribution and Gaussian distribution. It provides more security in data hiding and protection against new privacy threads. In the use of assessment analysis and outcome analysis, the real-world dataset repositories used.
