Abstract | ||
---|---|---|
We present a secure backpropagation neural network training model (SecureBP), which allows a neural network to be trained while retaining the confidentiality of the training data, based on the homomorphic encryption scheme. We make two contributions. The first one is to introduce a method to find a more accurate and numerically stable polynomial approximation of functions in a certain interval. The second one is to find a strategy of refreshing ciphertext during training, which keeps the order of magnitude of noise at O<mml:mo></mml:mover><mml:mfenced open="(" close=")" separators="|">e33</mml:mfenced>. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1155/2020/5328059 | SECURITY AND COMMUNICATION NETWORKS |
DocType | Volume | ISSN |
Journal | 2020.0 | 1939-0114 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qinju Liu | 1 | 0 | 0.34 |
Xianhui Lu | 2 | 85 | 18.52 |
Fucai Luo | 3 | 0 | 0.34 |
Shuai Zhou | 4 | 0 | 0.34 |
Jingnan He | 5 | 3 | 2.41 |
Kunpeng Wang | 6 | 15 | 6.71 |