Verifying Result Correctness of Outsourced Frequent Itemset in Data Mining through Probabilistic and deterministic approaches
Journal Title: International Journal of engineering Research and Applications - Year 2017, Vol 7, Issue 8
Abstract
Cloud computing technology has enabled large organization to outsource data to a third-party service provider (server) for data mining and has provided a natural solution for the data-mining paradigms. However, outsourcing raises a serious security and privacy issue. Data outsourcing is the key task in recent days, for accessing services of the database processing. For the client with the weak computational capacity, there is no assurance or guarantee to know if the server returned correct mining results or not. This paper focuses on the specific task of frequent item set mining. The server that is potentially untrusted and tries to escape from verification by using its prior knowledge of the outsourced data is considered. An efficient probabilistic and deterministic verification approach to check whether the server has returned correct and complete frequent item sets is proposed. This proposed verification approach can catch incorrect results with high probability and the deterministic approach measures the result correctness with 100% certainty. The result shows that the proposed efficient verification method is desirable for both the cases. And the effectiveness and efficiency of our method gives secure and faster results using an extensive set of empirical results on real datasets.
Authors and Affiliations
Dr. P. Julia Grace, Vanitha Suresh
Urban Courtyard Housing Form as a Response to Human Need, Culture and Environment in Hot Climate Regions: Baghdad as a Case Study
Courtyard housing is an important dwelling type in human history. It was founded in many ancient histories of different countries and climate zones. Many factors influenced certain types and forms of urban courtyard hous...
Can Empirical Descriptors Reliably Predict Molecular Lipophilicity ? A QSPR Study Investigation
Reliable prediction of lipophilicity in organic compounds involves molecular descriptors determination. In this work, the lipophilicity of a set of twenty-three molecules has been determined using up to seven various emp...
Is it necessary to measure all brain regions for the assessment of PAF?
From decades of research, electroencephalography (EEG) has been proved as a potential non-invasive medical technique to measure the electrophysiological activities of brain. Alpha is one of the most prominent frequency b...
Analyzing the Impact of Signal Strength and Network Size on Energy Consumed In MANET´s Using Fuzzy Logic
The Aim Of This Project Is To Study The Impact Of Changing The Signal Strength And Network Size On Energy Consumed Under Aodv Routing Protocol In Mobile Ad Hoc Network(Manets) Using Fuzzy Logic.From Simulation Results, W...
Sonar Target Characterization and Echo Separation Using the Fractional Fourier Transform and its Relation to the Wigner Distribution
In this paper, we apply the relationship between the Fractional Fourier Transform (FrFT) and the Wigner Distribution (WD) to identify and separate echoes from an active sonar based upon the characteristics of different t...