2013 | OriginalPaper | Buchkapitel
Privacy Preserving Distributed K-Means Clustering in Malicious Model Using Zero Knowledge Proof
verfasst von : Sankita Patel, Viren Patel, Devesh Jinwala
Erschienen in: Distributed Computing and Internet Technology
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Preserving Privacy is crucial in distributed environments wherein data mining becomes a collaborative task among participants. Solutions proposed on the lines of cryptography involve use of classical cryptographic constructs in data mining algorithms. Applicability of solutions proposed depends on the adversary model in which it is able to preserve privacy. Existing cryptography based solutions for privacy preserving clustering aim to achieve privacy in presence of semi honest adversary model. For the practical applicability of the solutions in real world settings, support of malicious adversary model is desirable. As per our literature survey, the existing research lacks any fool proof solution for privacy preserving distributed clustering in malicious adversary model. In this paper, we propose privacy preserving distributed K-Means clustering of horizontally partitioned data that supports privacy in malicious adversarial model. The basic construct involves use of secret sharing mechanism clubbed with code based zero knowledge identification scheme. We use secret sharing for privately sharing the information and code based identification scheme to add support against malicious adversaries.