Non-interactive privacy preserving recurrent neural network prediction with homomorphic encryption

R Podschwadt, D Takabi - 2021 IEEE 14th International …, 2021 - ieeexplore.ieee.org
2021 IEEE 14th International Conference on Cloud Computing (CLOUD), 2021ieeexplore.ieee.org
Neural networks have enabled many new and interesting applications in a wide variety of
domains. However, deep learning models are very computationally expensive and
outsourcing the computation to the Cloud creates privacy concerns. Homomorphic
encryption (HE) allows computation on encrypted data, thus preserving its privacy. Common
neural networks architectures, such as CNNs and fully connected networks, have been
adapted for HE. However, there is very little work on recurrent neural networks (RNNs) …
Neural networks have enabled many new and interesting applications in a wide variety of domains. However, deep learning models are very computationally expensive and outsourcing the computation to the Cloud creates privacy concerns. Homomorphic encryption (HE) allows computation on encrypted data, thus preserving its privacy. Common neural networks architectures, such as CNNs and fully connected networks, have been adapted for HE. However, there is very little work on recurrent neural networks (RNNs). Existing solutions for RNNs over encrypted data require interaction between the data owner and the Cloud. In this paper, we present parallel RNN blocks, an RNN architecture that can be run on encrypted data without client-server interaction. We describe our proposed approach and evaluate it on a real-world dataset of online product reviews and IMDb movie reviews. Our results are promising; we can achieve 88.8% F1 score on the product reviews. The model generalizes well to the IMDb data set with a 74.36% F1 score using our proposed architecture. The performance is within 3 percentage points of our baseline.
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果