Privacy is the most important issue in data publishing. Many of the organizations will distribute Individuals personal data for research and survey purpose. Confidence is considered as highest priority to be revealed during publishing the data which means that an adversary cannot predict sensitive information. In addition to that another important problem to be considered is that the adversary may also have access to external knowledge like public records and social networks related to the individuals. A unique multidimensional technique to measuring an adversary's external knowledge is also presented, along with a generic framework for privacy reasoning in the presence of external knowledge. In high dimensional space, the data become sparse, making it difficult to understand the idea of spatial locality. Data anonymization has received considerable attention due to the need of several organizations to release microdata without revealing the identity of individuals. Finally the impact of dimensionality on k-anonymity techniques is examined.

Full text: IJEIR_2944_FINAL.pdf