An Improved Secure High-Order-Lanczos Based Orthogonal Tensor SVD for Outsourced Cyber-Physical-Social Big Data Reduction

Abstract

Cyber-physical-social big data concern heterogeneous, multiaspect, large-volume data generated in cyber-physical-social systems (CPSS). Orthogonal tensor SVD (OTSVD) has emerged as a powerful tool to reduce cyber-physical-social big data. In this work, we propose an improved secure high-order-Lanczos based OTSVD for cyber-physical-social big data reduction in clouds. Specifically, to take advantage of the parallel processing capability of cloud computing, the improved secure high-order Lanczos algorithm is derived by restructuring the original high-order Lanczos algorithm such that only one synchronization point per iteration is required. To protect data privacy, the improved secure high-order-Lanczos based OTSVD employs homomorphic encryption integrated with batching technique, and garbled circuits, and makes all computations of the OTSVD algorithm in clouds come true. To our knowledge, this is the first study to efficiently tackle big data reduction in clouds in a privacy-preserving manner. Finally, we prove that our improved approach is secure in semi-trusted model. And we evaluate the proposed improved secure OTSVD on real datasets. The results show that our proposed improved secure approach is efficient and scalable for cyber-physical-social big data reduction.