Towards Efficient and Secure Delivery of Data for Training and Inference with Privacy-Preserving

The adoption of deep learning technology has been slowed down by privacy concerns, as many sensitive data are prohibited from sharing to third party for deep neural network development. In this paper, we present \textit{Morphed Learning} (MoLe), an efficient and secure scheme for delivering deep learning data. MoLe is consisted of data morphing and Augmented Convolutional (Aug-Conv) layer. Data morphing allows the data provider to send morphed data without privacy information, while Aug-Conv layer helps the deep learning developer apply their network on the morphed data without performance penalty. Theoretical analysis show that MoLe can provide strong security with overhead non-related to dataset size or the depth of neural network. Specifically, using MoLe for VGG-16 network on CIFAR dataset, the computational overhead is 9\% and data transmission overhead is 5.12\%. Meanwhile the attack success probability for the adversary is $7.9 \times 10^{-90}.$