Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper)

Yidan Zhang, Marino Anthony James James, Jiageng Chen, Chunhua Su, Jinguang Han

Research output: Book/ReportBook

1 Citation (Scopus)

Abstract

Modern cryptographic schemes have been focusing on protecting attacks from computational bounded adversaries. The various cryptographic primitives are designed concretely following some randomization design strategies, so that one of the goals is to make it hard for the attacker to distinguish between the real ciphers and the randomly distributed ones. Recently, Google Brain team proposed the idea to build cryptographic scheme automatically based on the neural network, and they claim that the scheme can defeat neural network adversaries. While it is a whole new direction, the security of the underlined scheme is remained unknown. In this paper, we investigate their basic statistical behavior from traditional cryptography’s point of view and extend their original scheme to discuss how the encryption protocol behave under a much more stronger adversary.
Original languageUndefined/Unknown
PublisherSpringer
DOIs
Publication statusPublished - 2017
Externally publishedYes

Publication series

Name
NameInternational Conference on Information Security Practice and Experience - ISPEC 2017
PublisherSpringer
Volume10701

Cite this

Zhang, Y., James, M. A. J., Chen, J., Su, C., & Han, J. (2017). Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper). (International Conference on Information Security Practice and Experience - ISPEC 2017; Vol. 10701). Springer. https://doi.org/10.1007/978-3-319-72359-4_34
Zhang, Yidan ; James, Marino Anthony James ; Chen, Jiageng ; Su, Chunhua ; Han, Jinguang. / Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper). Springer, 2017. (International Conference on Information Security Practice and Experience - ISPEC 2017).
@book{ab568e1e9ecf499589af7c2d50926389,
title = "Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper)",
abstract = "Modern cryptographic schemes have been focusing on protecting attacks from computational bounded adversaries. The various cryptographic primitives are designed concretely following some randomization design strategies, so that one of the goals is to make it hard for the attacker to distinguish between the real ciphers and the randomly distributed ones. Recently, Google Brain team proposed the idea to build cryptographic scheme automatically based on the neural network, and they claim that the scheme can defeat neural network adversaries. While it is a whole new direction, the security of the underlined scheme is remained unknown. In this paper, we investigate their basic statistical behavior from traditional cryptography’s point of view and extend their original scheme to discuss how the encryption protocol behave under a much more stronger adversary.",
author = "Yidan Zhang and James, {Marino Anthony James} and Jiageng Chen and Chunhua Su and Jinguang Han",
year = "2017",
doi = "10.1007/978-3-319-72359-4_34",
language = "Undefined/Unknown",
publisher = "Springer",

}

Zhang, Y, James, MAJ, Chen, J, Su, C & Han, J 2017, Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper). International Conference on Information Security Practice and Experience - ISPEC 2017, vol. 10701, Springer. https://doi.org/10.1007/978-3-319-72359-4_34

Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper). / Zhang, Yidan; James, Marino Anthony James; Chen, Jiageng; Su, Chunhua; Han, Jinguang.

Springer, 2017. (International Conference on Information Security Practice and Experience - ISPEC 2017; Vol. 10701).

Research output: Book/ReportBook

TY - BOOK

T1 - Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper)

AU - Zhang, Yidan

AU - James, Marino Anthony James

AU - Chen, Jiageng

AU - Su, Chunhua

AU - Han, Jinguang

PY - 2017

Y1 - 2017

N2 - Modern cryptographic schemes have been focusing on protecting attacks from computational bounded adversaries. The various cryptographic primitives are designed concretely following some randomization design strategies, so that one of the goals is to make it hard for the attacker to distinguish between the real ciphers and the randomly distributed ones. Recently, Google Brain team proposed the idea to build cryptographic scheme automatically based on the neural network, and they claim that the scheme can defeat neural network adversaries. While it is a whole new direction, the security of the underlined scheme is remained unknown. In this paper, we investigate their basic statistical behavior from traditional cryptography’s point of view and extend their original scheme to discuss how the encryption protocol behave under a much more stronger adversary.

AB - Modern cryptographic schemes have been focusing on protecting attacks from computational bounded adversaries. The various cryptographic primitives are designed concretely following some randomization design strategies, so that one of the goals is to make it hard for the attacker to distinguish between the real ciphers and the randomly distributed ones. Recently, Google Brain team proposed the idea to build cryptographic scheme automatically based on the neural network, and they claim that the scheme can defeat neural network adversaries. While it is a whole new direction, the security of the underlined scheme is remained unknown. In this paper, we investigate their basic statistical behavior from traditional cryptography’s point of view and extend their original scheme to discuss how the encryption protocol behave under a much more stronger adversary.

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85038076233&partnerID=MN8TOARS

U2 - 10.1007/978-3-319-72359-4_34

DO - 10.1007/978-3-319-72359-4_34

M3 - Book

BT - Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper)

PB - Springer

ER -

Zhang Y, James MAJ, Chen J, Su C, Han J. Automatic encryption schemes based on the neural networks: Analysis and discussions on the various adversarial models (short paper). Springer, 2017. (International Conference on Information Security Practice and Experience - ISPEC 2017). https://doi.org/10.1007/978-3-319-72359-4_34