Neural Network Wiretap Code Design for Multi-Mode Fiber Optical Channels

Research output: Contribution to book/Conference proceedings/Anthology/ReportConference contributionContributedpeer-review

Contributors

Abstract

The design of reliable and secure codes with finite block length is an important requirement for industrial machine type communications. In this work, we develop an autoencoder for the multi-mode fiber wiretap channel taking into account the error performance at the legitimate receiver and the information leakage at potential eavesdroppers. The estimate of the mutual information leakage includes AWGN and fading channels. The code design is tailored to the specific channel setup where the eavesdropper experiences a mode dependent loss. Numerical simulations illustrate the performance and show a Pareto improvement of the proposed scheme compared to the state-of-the-art polar wiretap codes.

Details

Original languageEnglish
Title of host publicationICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages8738-8742
Number of pages5
ISBN (print)978-1-5090-6632-2
Publication statusPublished - 8 May 2020
Peer-reviewedYes

Conference

TitleICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Duration4 - 8 May 2020
LocationBarcelona, Spain

External IDs

Scopus 85089224631

Keywords

Keywords

  • Optical fibers, Optical design, Optical computing, Optical fiber networks, Numerical simulation, Optical receivers, Optical signal processing