HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture

Qian Lou, Lei Jiang
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7102-7110, 2021.

Abstract

Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet for smaller computing overhead, but we find naïvely using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a \textbf{HE}-friendly privacy-preserving \textbf{M}obile neural n\textbf{ET}work architecture, \textbf{HEMET}. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by $59.3%\sim 61.2%$, and improves the inference accuracy by $0.4 % \sim 0.5%$.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-lou21a, title = {HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture}, author = {Lou, Qian and Jiang, Lei}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {7102--7110}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/lou21a/lou21a.pdf}, url = {https://proceedings.mlr.press/v139/lou21a.html}, abstract = {Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet for smaller computing overhead, but we find naïvely using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a \textbf{HE}-friendly privacy-preserving \textbf{M}obile neural n\textbf{ET}work architecture, \textbf{HEMET}. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by $59.3%\sim 61.2%$, and improves the inference accuracy by $0.4 % \sim 0.5%$.} }
Endnote
%0 Conference Paper %T HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture %A Qian Lou %A Lei Jiang %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-lou21a %I PMLR %P 7102--7110 %U https://proceedings.mlr.press/v139/lou21a.html %V 139 %X Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet for smaller computing overhead, but we find naïvely using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a \textbf{HE}-friendly privacy-preserving \textbf{M}obile neural n\textbf{ET}work architecture, \textbf{HEMET}. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by $59.3%\sim 61.2%$, and improves the inference accuracy by $0.4 % \sim 0.5%$.
APA
Lou, Q. & Jiang, L.. (2021). HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:7102-7110 Available from https://proceedings.mlr.press/v139/lou21a.html.

Related Material