A Study on Privacy Preserving Techniques in Data Mining

Abstract

Data Mining (DM) is the technique of examining data from specific summarizing and perspectives the outcome as useful information. It has been describing as "the non-trivial procedure of new, potentially helpful and ultimately conceivable patterns and identifying valid in data". The word “Knowledge” in KDD submits to the discovery of example which is removing since the processed data. Preserving privacy is becoming a key apprehension as personal data is publicly available in recent years. The proper protection of private information is gradually becoming an important concern in an age where several countries have certain laws on these issues such as the misuse Individual Information Protection and Electronic Documents of individual data and fraud are across the board. Publishing information about individuals without showing delicate information about them is an important problem. Publishing individual data for big data analysis such as scientific research and merchant analysis has become regular in this decade. Anonym zed information distribution has gotten significant consideration from the examination group as of late. For arithmetical responsive feature, mainly of the available personal-preserving data publish method contemplate on top of micro-data with several definite responsive attribute otherwise merely one arithmetical responsive characteristic. During this paper, Entropy l-diversity + k-Anonymity (ED-kA) technique used to rise the retreat of the data.

Keywords: Data mining, ED-kA technique, KDD(knowledge discovery in databases), preserving privacy

Cite this Article
Ashutosh Sharma, Ashish Gupta. A Study on Privacy-preserving Techniques in Data Mining. Journal of Operating Systems Development & Trends. 2018; 5(2): 18–23p.