Integrity verification of cloud-hosted data analytics computations
Hui Wang · 2012
In this position paper, we present efficient and practical integrity verification techniques that check whether the untrusted cloud has returned correct result of outsourced data analytics computations. We consider the computation of summation form that is used in a large class of machine learning and data mining problems. We discuss our verification techniques for both non-collusive and collusive malicious workers in MapReduce.