Knowledge Discovery In Data Mining

Knowledge discovery also known as data mining is the processes involve penetration into tremendous amount of data with the support from computer and web technology for examining the data. Data mining is a process of discovering interesting knowledge by extracting or mining the data fromlarge amount of data and the process of finding correlations or patterns among dozens of fields in large relational databases [3, 4]. Privacy Preserving in Data Publishing (PPDP) is very important in data mining when publishing individual information on web [3].

The improvements are toward producing more effective methods that preserve the privacy and also reduces information loss to the researchers. There are also researches related to improvements of the algorithm that avoids some attacks on data. Rapid advances in data collection and storage technology have enabled organizations to accumulate vast amount of data. Simple transactions of everyday life such as using a cash card, credit card, a telephone monitoring system or browsing the web lead to automated data storage. In many cases, these large volumes of data can be mined for

First one is the un-trusted model and second one is trusted model. In the un-trusted model, the data holder is not trusted and may try to discover sensitive information from record owners. Various cryptographic solutions, statistical methods, andanonymous communicationswere proposed to collect records anonymously from their owners without revealing the owners identity. In the trusted model, the data holder is trustworthy and record owners are willing to provide their personal information to the data holder; however, the trust is not transitive to the data recipient. In this case data recipient can attempt to identify sensitive information of record owners. In this Dissertation we have considered the trusted model and focus on the issues at the recipient side when publishing the