Abstract: Data Privacy is one of the major issues while storing the Data in a database environment. Data Mining based attacks, a major threat to the data, allows an adversary or an unauthorized user to infer valuable and sensitive information by analyzing the results generated from computation performed on the raw data. This paper presents an approach to mine the data securely using k-means algorithm even in the presence of adversaries. This approach assumes that the data is not stored in a centralized location but is distributed to various hosts. This proposed approach prevents any intermediate data leakage in the process of computation while maintaining the correctness and validity of the data mining process and the end results.

Keywords: Data Mining, Security, K-means, Encryption.