elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

A fast reservoir computing based image encryption algorithm

Köglmayr, Daniel and Räth, Christoph (2023) A fast reservoir computing based image encryption algorithm. In: 2023 International Joint Conference on Neural Networks, IJCNN 2023. International Joint Conference on Neural Networks (IJCNN), 18.-23. Juni 2023, Gold Coast, Australien. doi: 10.1109/IJCNN54540.2023.10191083. ISBN 978-166548867-9.

[img] PDF - Only accessible within DLR bis June 2024
13MB

Official URL: https://ieeexplore.ieee.org/document/10191083

Abstract

Reservoir computing has gained a lot of momentum in recent years, in part due to its high-speed performance. The algorithm presented here deliberately exploits this property for efficient encryption and decryption of image data. It is demonstrated that its performance is a factor of 1000 faster than another encryption algorithm based on reservoir computing. We further extend the presented method for applicability to high-resolution and color images by exploiting the computational speed of small reservoir networks and the property that reservoir computers are generally able to reproduce their training data with high accuracy. To that, security and performance aspects are discussed.

Item URL in elib:https://elib.dlr.de/196434/
Document Type:Conference or Workshop Item (Poster)
Title:A fast reservoir computing based image encryption algorithm
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Köglmayr, DanielUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Räth, ChristophUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:2023
Journal or Publication Title:2023 International Joint Conference on Neural Networks, IJCNN 2023
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
DOI:10.1109/IJCNN54540.2023.10191083
ISBN:978-166548867-9
Status:Published
Keywords:AI, encryption, reservoir computing
Event Title:International Joint Conference on Neural Networks (IJCNN)
Event Location:Gold Coast, Australien
Event Type:international Conference
Event Dates:18.-23. Juni 2023
Organizer:IEEE
HGF - Research field:other
HGF - Program:other
HGF - Program Themes:other
DLR - Research area:Digitalisation
DLR - Program:D DAT - Data
DLR - Research theme (Project):D - short study [DAT]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute for AI Safety and Security
Deposited By: Räth, Christoph
Deposited On:11 Aug 2023 12:24
Last Modified:15 Sep 2023 08:12

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.