Efficient image encryption and compression based on a VAE generative model

Efficient image encryption and compression not only well protect the security of image information, but also greatly reduce the bandwidth. This paper proposes an image encryption method based on variational auto-encoder generation model. Firstly, we use the random gradient method to train the variational auto-encoder generation model, and iteration times of the model is determined comprehensively by the training time, the loss function and the reconstruction image. The peak signal-to-noise ratio and mean square error are used to measure the compression effect of the model. Secondly, we utilize the two trained image data divisions to change the data of the generated model, and to generate an encryption image. Finally, this paper uses Spyder to simulate experiments and analyze the results. The experimental results show that the method is fast and easy to encrypt, the algorithm is simple and the distortion rate of the decrypt image is low, and it is strong practicality.

[1]  Shiguang Shan,et al.  Stacked Progressive Auto-Encoders (SPAE) for Face Recognition Across Poses , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Aaron C. Courville,et al.  Discriminative Regularization for Generative Models , 2016, ArXiv.

[3]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[4]  Max Welling,et al.  Markov Chain Monte Carlo and Variational Inference: Bridging the Gap , 2014, ICML.

[5]  Xinpeng Zhang,et al.  Effective reversible data hiding in encrypted image with privacy protection for image content , 2015, J. Vis. Commun. Image Represent..

[6]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[7]  Chin-Chen Chang,et al.  A Novel Joint Data-Hiding and Compression Scheme Based on SMVQ and Image Inpainting , 2014, IEEE Transactions on Image Processing.

[8]  Weiming Zhang,et al.  On the fault-tolerant performance for a class of robust image steganography , 2018, Signal Process..

[9]  Li Li,et al.  An image compression and encryption scheme based on deep learning , 2016, ArXiv.

[10]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[11]  Uday B. Desai,et al.  PCA Encrypted Short Acoustic Data Inculcated in Digital Color Images , 2015, Int. J. Comput. Commun. Control.

[12]  Seong Oun Hwang,et al.  A compression sensing and noise-tolerant image encryption scheme based on chaotic maps and orthogonal matrices , 2016, Neural Computing and Applications.

[13]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[14]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[15]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[16]  Daan Wierstra,et al.  Towards Conceptual Compression , 2016, NIPS.

[17]  Chuan Qin,et al.  Reversible data hiding in encrypted image with separable capability and high embedding capacity , 2018, Inf. Sci..

[18]  Xinpeng Zhang,et al.  Fragile image watermarking with pixel-wise recovery based on overlapping embedding strategy , 2017, Signal Process..

[19]  Allen Gersho,et al.  Vector Quantization I:Structure and Performance , 1992 .

[20]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[21]  Bhupendra Gupta,et al.  Image Denoising Using Spatial Gradient Based Bilateral Filter and Minimum Mean Square Error Filtering , 2015 .

[22]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[23]  Xingming Sun,et al.  Partial Encryption of Color Image Using Quaternion Discrete Cosine Transform , 2015 .

[24]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[25]  Luis Gonzalo Sanchez Giraldo.  Revisiting Denoising Auto-Encoders , 2017 .

[26]  Valero Laparra,et al.  End-to-end Optimized Image Compression , 2016, ICLR.

[27]  Xiangyang Luo,et al.  Selection of Rich Model Steganalysis Features Based on Decision Rough Set $\alpha$ -Positive Region Reduction , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  David Minnen,et al.  Full Resolution Image Compression with Recurrent Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).