Chaotic Deep Network for Mobile D2D Communication

Device-to-Device (D2D) communication has now become one of the most promising technologies in wireless communications of the Internet of Things (IoT). In view of the requirements on data security, response speed, signal decryption quality and storage cost of mobile devices in D2D networks, we propose chaotic deep network (CDN) to achieve secure transmission which is swifter, higher quality and lower cost. The proposed scheme consists of a prepositive nonrepetitive training procedure, a well-designed parallel encryption process, and a set of pretrained chaotic deep neural decryption networks. Benefiting from the utilization of deep learning methods, CDN achieves the swift and accurate decryption at a much lower sampling rate, which brings huge dimension reduction of both measurement matrices and ciphertext signals. Also, chaotic initial values and parameters are applied to matrix generation and network training, leading to great time reduction, storage saving and security improvement. In addition, CDN incorporates the frameworks of semitensor product (STP) and block-based image processing (BIP), which not only breaks through the dimension matching limitation of matrix multiplication by using STP but also maintains the parallelizable block-cipher mode of BIP. Proved by experiments, CDN at the sampling ratio of 25% achieves almost the same or even better peak signal to noise ratio compared to other 8 most frequently used methods at that of 50% for the same test images, and obtains better visual effects. When using a large-sized image of $2^{10}\times 2^{10}$ pixels for the experiments, CDN is dozens and even hundreds of times faster than those methods, while reduces the size of measurement matrix from a 500-kB level to a 3-kB level, and the size of compressed data to be transmitted can be reduced by more than 50% as well. Besides, the total key space is approximately $10^{93}$ . The adjacent pixel correlation is less than 0.01.

[1]  Lixiang Li,et al.  Flexible and Secure Data Transmission System Based on Semitensor Compressive Sensing in Wireless Body Area Networks , 2019, IEEE Internet of Things Journal.

[2]  Claude E. Shannon,et al.  Communication theory of secrecy systems , 1949, Bell Syst. Tech. J..

[3]  Zongben Xu,et al.  ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Chen Chen,et al.  Compressed-sensing recovery of images and video using multihypothesis predictions , 2011, 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).

[5]  Dai-zhanCheng On Semi—tensor Product of Matrices and Its Applications , 2003 .

[6]  Yin Zhang,et al.  An efficient augmented Lagrangian method with applications to total variation minimization , 2013, Computational Optimization and Applications.

[7]  Michael Elad,et al.  A Deep Learning Approach to Block-based Compressed Sensing of Images , 2016, ArXiv.

[8]  Bin Wang,et al.  Image Encryption based on Chaotic Map and Reversible Integer Wavelet Transform , 2014 .

[9]  Yongdong Zhang,et al.  DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing , 2017, Neurocomputing.

[10]  Xiao Lan,et al.  Investigating the Multi-Ciphersuite and Backwards-Compatibility Security of the Upcoming TLS 1.3 , 2019, IEEE Transactions on Dependable and Secure Computing.

[11]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Seiichi Uchida,et al.  A parallel image encryption method based on compressive sensing , 2012, Multimedia Tools and Applications.

[13]  Lixiang Li,et al.  Secure and Energy-Efficient Data Transmission System Based on Chaotic Compressive Sensing in Body-to-Body Networks , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[14]  Quan Liu,et al.  A novel image encryption algorithm based on chaos maps with Markov properties , 2015, Commun. Nonlinear Sci. Numer. Simul..

[15]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[16]  Qiang Zhang,et al.  Improved algorithm for image encryption based on DNA encoding and multi-chaotic maps , 2014 .

[17]  Xuemin Shen,et al.  An LDPC Code Based Physical Layer Message Authentication Scheme With Prefect Security , 2018, IEEE Journal on Selected Areas in Communications.

[18]  Claude Castelluccia,et al.  Shake them up!: a movement-based pairing protocol for CPU-constrained devices , 2005, MobiSys '05.

[19]  Lixiang Li,et al.  Efficient and Secure Image Communication System Based on Compressed Sensing for IoT Monitoring Applications , 2020, IEEE Transactions on Multimedia.

[20]  Pavan K. Turaga,et al.  ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Pavan Turaga,et al.  Convolutional Neural Networks for Noniterative Reconstruction of Compressively Sensed Images , 2017, IEEE Transactions on Computational Imaging.

[22]  Mohsen Guizani,et al.  Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications , 2015, IEEE Communications Surveys & Tutorials.

[23]  Nikos Deligiannis,et al.  Measurement matrix design for compressive sensing with side information at the encoder , 2016, 2016 IEEE Statistical Signal Processing Workshop (SSP).

[24]  Yu Cheng,et al.  Security Analysis of Mobile Device-to-Device Network Applications , 2019, IEEE Internet of Things Journal.

[25]  Bernard Ghanem,et al.  ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Yu Cheng,et al.  Development of Mobile Ad-hoc Networks over Wi-Fi Direct with off-the-shelf Android phones , 2016, 2016 IEEE International Conference on Communications (ICC).

[27]  Byeungwoo Jeon,et al.  Multi-Scale Deep Compressive Sensing Network , 2018, 2018 IEEE Visual Communications and Image Processing (VCIP).

[28]  Lixiang Li,et al.  P-Tensor Product in Compressed Sensing , 2019, IEEE Internet of Things Journal.

[29]  Rongxing Lu,et al.  Channel Precoding Based Message Authentication in Wireless Networks: Challenges and Solutions , 2018, IEEE Network.

[30]  Fengbo Ren,et al.  LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction , 2018, ECCV.

[31]  Pavan K. Turaga,et al.  ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements , 2016, ArXiv.

[32]  Yishuang Geng,et al.  Content Distribution Mechanism in Mobile P2P Network , 2014, J. Networks.

[33]  Sherali Zeadally,et al.  Intelligent Device-to-Device Communication in the Internet of Things , 2016, IEEE Systems Journal.

[34]  Guangming Shi,et al.  Perceptual Compressive Sensing , 2018, PRCV.

[35]  Wuzhen Shi,et al.  Deep networks for compressed image sensing , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[36]  Feng Jiang,et al.  Image Compressed Sensing Using Convolutional Neural Network , 2020, IEEE Transactions on Image Processing.

[37]  Qing Wang,et al.  A Survey on Device-to-Device Communication in Cellular Networks , 2013, IEEE Communications Surveys & Tutorials.

[38]  Jianhui Wu,et al.  Image encryption and compression based on kronecker compressed sensing and elementary cellular automata scrambling , 2016 .

[39]  Michael Elad,et al.  Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[40]  Yong Guan,et al.  Practical security scheme design for resource-constrained wireless networks , 2009 .

[41]  Richard G. Baraniuk,et al.  A deep learning approach to structured signal recovery , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[42]  Jianhua Wu,et al.  Novel hybrid image compression–encryption algorithm based on compressive sensing , 2014 .

[43]  Jiantao Zhou,et al.  A Review of Compressive Sensing in Information Security Field , 2016, IEEE Access.

[44]  Yann LeCun,et al.  Learning Fast Approximations of Sparse Coding , 2010, ICML.

[45]  Joel A. Tropp,et al.  Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit , 2007, IEEE Transactions on Information Theory.

[46]  Zhongcheng Li,et al.  Opportunistic Routing in Intermittently Connected Mobile P2P Networks , 2013, IEEE Journal on Selected Areas in Communications.

[47]  Bharat K. Bhargava,et al.  Peer-to-peer file-sharing over mobile ad hoc networks , 2004, IEEE Annual Conference on Pervasive Computing and Communications Workshops, 2004. Proceedings of the Second.

[48]  Ning Zhang,et al.  Sec-D2D: A Secure and Lightweight D2D Communication System With Multiple Sensors , 2019, IEEE Access.

[49]  Ali Mousavi,et al.  Learning to invert: Signal recovery via Deep Convolutional Networks , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[50]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[51]  James E. Fowler,et al.  Block Compressed Sensing of Images Using Directional Transforms , 2010, 2010 Data Compression Conference.