Next Article in Journal
Improvements on Making BKW Practical for Solving LWE
Next Article in Special Issue
Cryptography as the Means to Protect Fundamental Human Rights
Previous Article in Journal / Special Issue
On General Data Protection Regulation Vulnerabilities and Privacy Issues, for Wearable Devices and Fitness Tracking Applications
Article

Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms

School of Electrical and Computer Engineering, Xiamen University Malaysia, Sepang 43900, Malaysia
*
Author to whom correspondence should be addressed.
Academic Editors: Seyit A. Camtepe and Josef Pieprzyk
Received: 23 September 2021 / Revised: 13 October 2021 / Accepted: 23 October 2021 / Published: 24 October 2021
(This article belongs to the Special Issue Cryptography: A Cybersecurity Toolkit)
This paper studies the use of deep learning (DL) models under a known-plaintext scenario. The goal of the models is to predict the secret key of a cipher using DL techniques. We investigate the DL techniques against different ciphers, namely, Simplified Data Encryption Standard (S-DES), Speck, Simeck and Katan. For S-DES, we examine the classification of the full key set, and the results are better than a random guess. However, we found that it is difficult to apply the same classification model beyond 2-round Speck. We also demonstrate that DL models trained under a known-plaintext scenario can successfully recover the random key of S-DES. However, the same method has been less successful when applied to modern ciphers Speck, Simeck, and Katan. The ciphers Simeck and Katan are further investigated using the DL models but with a text-based key. This application found the linear approximations between the plaintext–ciphertext pairs and the text-based key. View Full-Text
Keywords: deep learning; multilayer perceptron; convolutional neural network; long short-term memory; cryptanalysis; S-DES; Speck; Simeck; Katan deep learning; multilayer perceptron; convolutional neural network; long short-term memory; cryptanalysis; S-DES; Speck; Simeck; Katan
Show Figures

Figure 1

MDPI and ACS Style

Chong, B.Y.; Salam, I. Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms. Cryptography 2021, 5, 30. https://0-doi-org.brum.beds.ac.uk/10.3390/cryptography5040030

AMA Style

Chong BY, Salam I. Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms. Cryptography. 2021; 5(4):30. https://0-doi-org.brum.beds.ac.uk/10.3390/cryptography5040030

Chicago/Turabian Style

Chong, Bang Y., and Iftekhar Salam. 2021. "Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms" Cryptography 5, no. 4: 30. https://0-doi-org.brum.beds.ac.uk/10.3390/cryptography5040030

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop