PROJECT TITLE :

Privacy Preserving Deep Computation Model on Cloud for Big Data Feature Learning

ABSTRACT:

To enhance the efficiency of massive knowledge feature learning, the paper proposes a privacy preserving deep computation model by offloading the expensive operations to the cloud. Privacy concerns become evident as a result of there are a giant variety of personal data by numerous applications in the good city, like sensitive data of governments or proprietary information of enterprises. To protect the private information, the proposed model uses the BGV encryption scheme to encrypt the non-public data and employs cloud servers to perform the high-order back-propagation algorithm on the encrypted knowledge efficiently for deep computation model training. Furthermore, the proposed scheme approximates the Sigmoid perform as a polynomial operate to support the secure computation of the activation operate with the BGV encryption. In our scheme, only the encryption operations and the decryption operations are performed by the shopper whereas all the computation tasks are performed on the cloud. Experimental results show that our theme is improved by approximately a pair of.five times in the coaching potency compared to the standard deep computation model while not disclosing the personal knowledge using the cloud computing as well as 10 nodes. A lot of importantly, our scheme is very scalable by employing a lot of cloud servers, that is significantly suitable for big information.