چکیده:
In recent privacy has emerged as one of the major concerns of deep learning, since it requires huge amount of personal data. Medical Image Analysis is one of the prominent areas where sensitive data are shared to a third party service provider. In this paper, a secure deep learning scheme called Metamorphosed Learning (MpLe) is proposed to protect the privacy of images in medical image analysis. An augmented convolutional layer and image morphing are two main components of MpLe scheme. Data providers morph the images without privacy information using image morphing component. The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty. MpLe provides sturdy security and privacy with optimal computational overhead. The proposed scheme is experimented using VGG-16 network on CIFAR dataset. The performance of MpLe is compared with similar works such as GAZELLE and MiniONN and found that the MpLe attracts very less computational and data transmission overhead. MpLe is also analyzed for various adversarial attack and realized that the success rate is as low as . The efficiency of the proposed scheme is proved through experimental and performance analysis.
خلاصه ماشینی:
In this paper, a secure deep learning scheme called Metamorphosed Learning (MpLe) is proposed to protect the privacy of images in medical image analysis.
The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty.
, 2019; Phong & Phuong, 2019; Shokri & Shmatikov, 2015; Y.
MpLe is a secure and efficient privacy preserving scheme for deep learning based medical image analysis.
The proposed scheme is aimed to deliver the complete data for deep learning training while protecting the privacy of the images.
Augmented Convolution layer is the next major component of MpLe that inversely transforms the morphed data and replaces the first layer of the deep learning convolutional neural network (CNN).
Differential privacy mechanism to protect the deep learning model is proposed in (Abadi et al.
, 2017) a homomorphic encryption based scheme is proposed to protect the privacy of the deep learning model and the intermediate results.
Performance Evaluation of MpLe with GAZELLE and MiniONN Conclusion In this paper, we presented a privacy preserving scheme for deep learning network.
Experimental and performance analysis proved that our proposed scheme is efficient in protecting the privacy of the medical image data with minimal computational and communication overhead.
Privacy-preserving deep learning algorithm for big personal data analysis.
Privacy Preserving Deep Computation Model on Cloud for Big Data Feature Learning.
An Efficient Privacy-Preserving Deep Learning Scheme for Medical Image Analysis.
An Efficient Privacy-Preserving Deep Learning Scheme for Medical Image Analysis.