Flexible Design of Finite Blocklength Wiretap Codes by Autoencoders

With an increasing number of wireless devices, the risk of being eavesdropped increases as well. From information theory, it is well known that wiretap codes can asymptotically achieve vanishing decoding error probability at the legitimate receiver while also achieving vanishing leakage to eavesdroppers. However, under finite blocklength, there exists a tradeoff among different parameters of the transmission. In this work, we propose a flexible wiretap code design for Gaussian wiretap channels under finite blocklength by neural network autoencoders. We show that the proposed scheme has higher flexibility in terms of the error rate and leakage tradeoff, compared to the traditional codes.

[1]  Artemy Kolchinsky,et al.  Estimating Mixture Entropy with Pairwise Distances , 2017, Entropy.

[2]  Matthieu R. Bloch,et al.  Physical Layer Security , 2020, Encyclopedia of Wireless Networks.

[3]  Alexander Vardy,et al.  Achieving the Secrecy Capacity of Wiretap Channels Using Polar Codes , 2010, IEEE Transactions on Information Theory.

[4]  T. Charles Clancy,et al.  Convolutional Radio Modulation Recognition Networks , 2016, EANN.

[5]  Yair Be'ery,et al.  Learning to decode linear codes using deep learning , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[6]  H. Vincent Poor,et al.  Finite-blocklength bounds for wiretap channels , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[7]  Sreeram Kannan,et al.  Communication Algorithms via Deep Learning , 2018, ICLR.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  A. D. Wyner,et al.  The wire-tap channel , 1975, The Bell System Technical Journal.

[11]  Maxim Naumov,et al.  Parallel Complexity of Forward and Backward Propagation , 2017, ArXiv.

[12]  Imre Csiszár,et al.  Broadcast channels with confidential messages , 1978, IEEE Trans. Inf. Theory.

[13]  Eduard A. Jorswieck,et al.  Wiretap Code Design by Neural Network Autoencoders , 2020, IEEE Transactions on Information Forensics and Security.

[14]  Emil Björnson,et al.  Multiobjective Signal Processing Optimization: The way to balance conflicting metrics in 5G systems , 2014, IEEE Signal Processing Magazine.

[15]  Erdal Arikan,et al.  Channel Polarization: A Method for Constructing Capacity-Achieving Codes for Symmetric Binary-Input Memoryless Channels , 2008, IEEE Transactions on Information Theory.

[16]  Kiran Karra,et al.  Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention , 2016, 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[17]  Stephan ten Brink,et al.  On deep learning-based channel decoding , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).

[18]  Eduard A. Jorswieck,et al.  Machine Learning Assisted Wiretapping , 2018, 2018 52nd Asilomar Conference on Signals, Systems, and Computers.

[19]  Matthieu R. Bloch,et al.  Strong Secrecy From Channel Resolvability , 2011, IEEE Transactions on Information Theory.