Privacy-Preserving Deep Sequential Model with Matrix Homomorphic Encryption
Jaehee Jang, Younho Lee, Andrey Kim, Byunggook Na, Donggeon Yhee, Byounghan Lee, Jung Hee Cheon, Sungroh Yoon
Abstract
Making deep neural networks available as a service introduces privacy problems, for which homomorphic encryption of both model and user data potentially offers the solution at the highest privacy level. However, the difficulty of operating on homomorphically encrypted data has hitherto limited the range of operations available and the depth of networks. We introduce an extended CKKS scheme MatHEAAN to provide efficient matrix representations and operations together with improved noise control. Using the MatHEAAN we developed a deep sequential model with a gated recurrent unit called MatHEGRU. We evaluated the proposed model using sequence modeling, regression, and classification of images and genome sequences. We show that the hidden states of the encrypted model, as well as the results, are consistent with a plaintext model.