TY - GEN
T1 - Spying on chaos-based cryptosystems with reservoir computing
AU - Antonik, Piotr
AU - Gulina, Marvyn
AU - Pauwels, Jael
AU - Rontani, Damien
AU - Haelterman, Marc
AU - Massar, Serge
N1 - Funding Information:
This work was supported by the Interuniversity Attraction Poles Program (Belgian Science Policy) Project Photonics@be IAP P7-35, by the Fonds de la Recherche Scientifique (FRS-FNRS), and by the Action de Recherche Concertée of the Fédération Universitaire Wallonie-Bruxelles through Grant No. AUWB-2012-12/17-ULB9. P.A. and D.R gratefully acknowledge the support of AFOSR (grants No. FA-9550-15-1-0279 and FA-9550-17-1-0072) and Région Grand-Est.
Publisher Copyright:
© 2018 IEEE.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/10/10
Y1 - 2018/10/10
N2 - Reservoir computing is a machine learning approach to designing artificial neuralnetworks. Despite the significant simplification of the training process, theperformance of such systems is comparable to other digital algorithms on a seriesof benchmark tasks. Recent investigations have demonstrated the possibility ofperforming long-horizon predictions of chaotic systems using reservoir computing.In this work we show that a trained reservoir computer can reproduce sufficientlywell the properties a chaotic system, hence allowing full synchronisation. Weillustrate this behaviour on the Mackey-Glass and Lorenz systems. Furthermore, weshow that a reservoir computer can be used to crack chaos-based cryptographicprotocols and illustrate this on two encryption schemes.
AB - Reservoir computing is a machine learning approach to designing artificial neuralnetworks. Despite the significant simplification of the training process, theperformance of such systems is comparable to other digital algorithms on a seriesof benchmark tasks. Recent investigations have demonstrated the possibility ofperforming long-horizon predictions of chaotic systems using reservoir computing.In this work we show that a trained reservoir computer can reproduce sufficientlywell the properties a chaotic system, hence allowing full synchronisation. Weillustrate this behaviour on the Mackey-Glass and Lorenz systems. Furthermore, weshow that a reservoir computer can be used to crack chaos-based cryptographicprotocols and illustrate this on two encryption schemes.
KW - Reservoir computer
KW - Recurrent neurral network
KW - Echo state network
KW - Chaos based cryptography
KW - reservoir computing
KW - chaos-based cryptography
KW - eavesdropping
KW - chaos synchronisation
KW - Ordinateur réservoir
KW - Réseau de neurones récurrents
KW - Réseau d'état d'écho
KW - Cryptographie par chaos
UR - https://ieeexplore.ieee.org/document/8489102/
UR - http://www.mendeley.com/research/spying-chaosbased-cryptosystems-reservoir-computing
UR - http://www.scopus.com/inward/record.url?scp=85056521900&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2018.8489102
DO - 10.1109/IJCNN.2018.8489102
M3 - Conference contribution
SN - 978-1-5090-6014-6
VL - 2018-July
T3 - 2018 International Joint Conference on Neural Networks (IJCNN)
SP - 1
EP - 7
BT - 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
PB - IEEE
ER -