Spying on chaos-based cryptosystems with reservoir computing

Piotr Antonik, Marvyn Gulina, Jael Pauwels, Damien Rontani, Marc Haelterman, Serge Massar

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

Abstract

Reservoir computing is a machine learning approach to designing artificial neural
networks. Despite the significant simplification of the training process, the
performance of such systems is comparable to other digital algorithms on a series
of benchmark tasks. Recent investigations have demonstrated the possibility of
performing long-horizon predictions of chaotic systems using reservoir computing.
In this work we show that a trained reservoir computer can reproduce sufficiently
well the properties a chaotic system, hence allowing full synchronisation. We
illustrate this behaviour on the Mackey-Glass and Lorenz systems. Furthermore, we
show that a reservoir computer can be used to crack chaos-based cryptographic
protocols and illustrate this on two encryption schemes.
Original languageEnglish
Title of host publication2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
PublisherIEEE
Pages1-7
Number of pages7
Volume2018-July
ISBN (Electronic)978-1-5090-6014-6
ISBN (Print)978-1-5090-6014-6
DOIs
Publication statusPublished - 10 Oct 2018

Publication series

Name2018 International Joint Conference on Neural Networks (IJCNN)

Fingerprint

Chaotic systems
Chaos theory
Cryptography
Learning systems
Synchronization
Cracks
Glass

Keywords

  • Reservoir computer
  • Recurrent neurral network
  • Echo state network
  • Chaos based cryptography
  • reservoir computing
  • chaos-based cryptography
  • eavesdropping
  • chaos synchronisation

Cite this

Antonik, P., Gulina, M., Pauwels, J., Rontani, D., Haelterman, M., & Massar, S. (2018). Spying on chaos-based cryptosystems with reservoir computing. In 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings (Vol. 2018-July, pp. 1-7). [8489102] (2018 International Joint Conference on Neural Networks (IJCNN)). IEEE. https://doi.org/10.1109/IJCNN.2018.8489102
Antonik, Piotr ; Gulina, Marvyn ; Pauwels, Jael ; Rontani, Damien ; Haelterman, Marc ; Massar, Serge. / Spying on chaos-based cryptosystems with reservoir computing. 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Vol. 2018-July IEEE, 2018. pp. 1-7 (2018 International Joint Conference on Neural Networks (IJCNN)).
@inproceedings{70fa96db2dfc48e49c931ca8f0bcd7cf,
title = "Spying on chaos-based cryptosystems with reservoir computing",
abstract = "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.",
keywords = "Reservoir computer, Recurrent neurral network, Echo state network, Chaos based cryptography, reservoir computing, chaos-based cryptography, eavesdropping, chaos synchronisation, Ordinateur r{\'e}servoir, R{\'e}seau de neurones r{\'e}currents, R{\'e}seau d'{\'e}tat d'{\'e}cho, Cryptographie par chaos",
author = "Piotr Antonik and Marvyn Gulina and Jael Pauwels and Damien Rontani and Marc Haelterman and Serge Massar",
year = "2018",
month = "10",
day = "10",
doi = "10.1109/IJCNN.2018.8489102",
language = "English",
isbn = "978-1-5090-6014-6",
volume = "2018-July",
series = "2018 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",
pages = "1--7",
booktitle = "2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings",

}

Antonik, P, Gulina, M, Pauwels, J, Rontani, D, Haelterman, M & Massar, S 2018, Spying on chaos-based cryptosystems with reservoir computing. in 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. vol. 2018-July, 8489102, 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, pp. 1-7. https://doi.org/10.1109/IJCNN.2018.8489102

Spying on chaos-based cryptosystems with reservoir computing. / Antonik, Piotr; Gulina, Marvyn; Pauwels, Jael ; Rontani, Damien ; Haelterman, Marc; Massar, Serge.

2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Vol. 2018-July IEEE, 2018. p. 1-7 8489102 (2018 International Joint Conference on Neural Networks (IJCNN)).

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

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

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 -

Antonik P, Gulina M, Pauwels J, Rontani D, Haelterman M, Massar S. Spying on chaos-based cryptosystems with reservoir computing. In 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Vol. 2018-July. IEEE. 2018. p. 1-7. 8489102. (2018 International Joint Conference on Neural Networks (IJCNN)). https://doi.org/10.1109/IJCNN.2018.8489102