원문정보
초록
영어
Privacy is the word which can listen everywhere in the data mining for data preserving. It should be provided the security to the data in many ways. Privacy should be provided to the sensitive data and micro data. Hence more number of existing techniques has been introduced to provide sensitive data. Many third party service providers are showing interest to release the data which is collected for research purpose. Existing systems like k-anonymity, l-diversity and t-closeness are already existed but they can’t provide better privacy measures. Each existing method carries different types of problems. The t-closeness is the more flexible privacy model called (n,t)-closeness will provide the better privacy and usage. Proposed Closeness measures require Probability distribution that is assessed using Earth Mover’s Distance (EMD) measurement. In this paper, the graph based algorithm graph-EMD. Compare with tree-EMD, graph EMD performs more flexible. The number of unknown variables is reduced to O (N) from O (N2) of the original EMD. In this paper, with Graph-EMD is implemented and show the performance and efficiency.
목차
1. Introduction
2. Related Work
3. Literature Work
3.1. Definition k-anonymity
3.2. The L-diversity Principle
3.3. Distinct l-diversity
3.4. Probabilistic l-diversity
3.5. Entropy l-diversity
3.6. T-Closeness
3.7. (n, t)-closeness
3.8. Earth Mover's Distance
4. Graph- Earth Mover's Distance
4.1. Implementation
4.2. Key points about Proposed Work
5. Conclusion
References