Attack of Against Simplified Data Encryption Standard Cipher System Using Neural Networks

Abstract

<b>Problem statement:</b> The problem in cryptanalysis can be described as an unknown and the neural networks are ideal tools for black-box system identification. In this study, a mathematical black-box model is developed and system identification techniques are combined with adaptive system techniques, to construct the Neuro-Identifier. <b>Approach:</b> The Neuro-Identifier was discussed as a black-box model to attack the target cipher systems. <b>Results:</b> In this study this model is a new addition in cryptography that presented the methods of block (SDES) crypto systems discussed. The constructing of Neuro-Identifier mode achieved two objectives: The first one was to construct emulator of Neuro-model for the target cipher system, while the second was to (cryptanalysis) determine the key from given plaintext-ciphertext pair. <b>Conclusion:</b> Present the idea of the equivalent cipher system, which is identical 100% to the unknown system and that means that an unknown hardware, or software cipher system could be reconstructed without known the internal circuitry or algorithm of it

Neural Network Based Data Encryption: A Comparison Study among DES, AES, and HE Techniques

“…It requires only an 8-bit block, whereas the original DES requires 64 bits, which amounts to an eight-fold simplification. Alallayah et al [28] propose a new complementary model discussed in the block cryptosystem (SDES) approach. The neural recognition model is constructed to achieve two goals.…”

“…The network is an ideal tool for identifying black box systems. Alallayah et al [29] discuss the simplified DES (SDES) block encryption system. The neural recognition model was constructed to achieve two objectives.…”

Machine learning based cryptanalysis techniques: perspectives, challenges and future directions

“…They also demonstrated that the efficacy of the MLP network is dependent on the nonlinearity of the S-DES internal s-boxes. Previous revolutionary papers on S-DES or other simplified ciphers include [15], [16], [17], or [18]. In 2002, an unprecedented incident occurred when a public-key approach based on neural networks was hacked using evolutionary algorithms [22].…”

Research on Plaintext Restoration of AES Based on Neural Network

“…In this paper, the cyclic neural network (RNN) is used to find the path by minimizing the network cost function in the differential operation graph of the block cipher. In 2010, Alallayah et al [3][4][5] performed neural network-based cryptanalysis on classical cryptography, sequence ciphers, and simplified DES (SDES). They regard cryptanalysis as a black box problem, using neural networks as an ideal tool for identifying black boxes, combining system identification technology with adaptive system technology, and constructing a neuroidentifier that simulates the target cryptosystem.…”

“…The neural output is compared with the plaintext, and performance error indicators are established for analyzing the data to improve efficiency. In 2014, Danziger et al [9] used the method in [5] to find out the mapping relationship between plaintext, ciphertext, and key in SDES. When experiments are performed using 102,400 sample data, the keys of the first, second, and fifth bits of the 10-bit key can be obtained; when the number of samples is reduced to 2000, the keys of the first and second bits can be obtained.…”