TY - GEN
T1 - Privacy-Preserving Deep Sequential Model with Matrix Homomorphic Encryption
AU - Jang, Jaehee
AU - Lee, Younho
AU - Kim, Andrey
AU - Na, Byunggook
AU - Yhee, Donggeon
AU - Lee, Byounghan
AU - Cheon, Jung Hee
AU - Yoon, Sungroh
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/5/30
Y1 - 2022/5/30
N2 - 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.
AB - 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.
KW - artificial intelligence
KW - deep learning
KW - homomorphic encryption
KW - recurrent neural network
UR - https://www.scopus.com/pages/publications/85133184586
U2 - 10.1145/3488932.3523253
DO - 10.1145/3488932.3523253
M3 - Conference contribution
AN - SCOPUS:85133184586
T3 - ASIA CCS 2022 - Proceedings of the 2022 ACM Asia Conference on Computer and Communications Security
SP - 377
EP - 391
BT - ASIA CCS 2022 - Proceedings of the 2022 ACM Asia Conference on Computer and Communications Security
PB - Association for Computing Machinery, Inc
T2 - 17th ACM ASIA Conference on Computer and Communications Security 2022, ASIA CCS 2022
Y2 - 30 May 2022 through 3 June 2022
ER -