Multimode Fiber Transmission Matrix Inversion with Densely Connected Convolutional Network for Physical Layer Security

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

Abstract

For exploiting multimode fiber optic communication networks towards physical layer security, we have trained a neural network performing mode decomposition of 10 modes. The approach is based on intensity-only camera images and works in real-time.

Details

Original languageEnglish
Title of host publication2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (electronic)9781943580910
Publication statusPublished - May 2021
Peer-reviewedYes

Conference

Title41th Conference on Lasers and Electro-Optics
Abbreviated titleCLEO 2021
Conference number41
Duration9 - 14 May 2021
Website
LocationOnline
CitySan Jose
CountryUnited States of America