CryptoNets: applying neural networks to encrypted data with high throughput and accuracy
Citations
2,593 citations
Cites background from "CryptoNets: applying neural network..."
...With the recent advances in deep learning, privacy-preserving neural networks inference is also receiving a lot of research interest [10, 11, 14, 28, 40, 52, 54]....
[...]
1,573 citations
Additional excerpts
...encryption [106] and secure multiparty computation [107])....
[...]
1,317 citations
Cites background from "CryptoNets: applying neural network..."
...e the privacy of gradients and enhance the security of the system. With the recent advances in deep learning, privacy-preserving neural networks inference is also receiving a lot of research interests[10,11,14,28,40,52,54]. ACM Trans. Intell. Syst. Technol., Vol. 10, No. 2, Article 12. Publication date: February 2019. Federated Machine Learning: Concept and Applications 12:13 3.2 Federated Learning vs Distributed Machi...
[...]
1,164 citations
Cites methods from "CryptoNets: applying neural network..."
...Prior solutions either treat decimal numbers as integers and preserve full accuracy after multiplication by using a very large finite field [22], or utilize 2PC for boolean circuits to perform fixed-point [21]...
[...]
...Therefore, we also consider replacing the activation function with the square function f(u) = u(2), as recently proposed in [22] but for prediction only....
[...]
1,107 citations
Cites background from "CryptoNets: applying neural network..."
...s. A common approach has been to adapt ML models and their training procedures to ensure that (over)underflows are controlled, by operating on normalized quantities and relying on careful quantization [172, 14, 182, 77]. It has been known for several decades that any function can be securely computed, even in the presence of malicious adversaries [183]. While generic solutions exist, their performance characteristic...
[...]
References
73,978 citations
33,301 citations
5,770 citations
[...]
4,134 citations
3,173 citations