Neural Cryptography Based on Generalized Tree Parity Machine for Real-Life Systems

Traditional public key exchange protocols are based on algebraic number theory. In another perspective, neural cryptography, which is based on neural networks, has been emerging. It has been reported that two parties can exchange secret key pairs with the synchronization phenomenon in neural networks. Although there are various models of neural cryptography, called Tree Parity Machine (TPM), many of them are not suitable for practical use, considering efficiency and security. In this paper, we propose a Vector-Valued Tree Parity Machine (VVTPM), which is a generalized architecture of TPM models and can be more efficient and secure for real-life systems. In terms of efficiency and security, we show that the synchronization time of the VVTPM has the same order as the basic TPM model, and it can be more secure than previous results with the same synaptic depth.

Kombinasi Sinkronisasi Jaringan Syaraf Tiruan dan Vigenere Cipher untuk Optimasi Keamanan Informasi

Kriptografi pengubahan pesan asli menjadi disamarkan berguna menjaga kerahasiaan, integritas, keaslian, autentikasi pesan ketika proses komunikasi. Kriptografi klasik dengan subtitusi polialfabetik Vigenere memiliki tabel alphabet 26 baris yang relatif sederhana menjamin kerahasiaan. Kini pendekatan pembelajaran mesin Jaringan Syaraf Tiruan (JST) menjadi solusi layak untuk kriptografi dengan membentuk kunci rahasia dalam bobot jaringan sulit terpecahkan. Kunci dihasilkan dari bidirectional learning, dua pohon paritas saling tersinkronisasi dengan paramater hidden neuron, input neuron dan bobot. Sinkronisasi pada saluran publik dengan mengadopsi cara kerja Tree Parity Machine (TPM) dengan tipe feed forward. Pendekatan Kriptografi JST bermanfaat sebagai perlindungan dan serangan kriptografi. Penelitian ini memanfaatkan kombinasi sinkronisasi JST dan Vigenere dalam bentuk generator untuk optimasi pesan. Hasil pengujian kombinasi metode tidak berpengaruh dengan jumlah tampungan karakter pesan dan nilai parameter. Keunggulan kunci yang dihasilkan tidak bisa digunakan secara berulang meski nilai parameter sama, namun panjang karakter kunci berjumlah sama. Sisi fungsionalitas menghasilkan nilai 100%. Kata kunci: Kriptografi, Jaringan Syaraf Tiruan (JST), Tree Parity Machine (TPM), Vigenere Cipher Abstract Cryptography changes the original message to be disguised useful to maintain the security message. Vigenere polyalphabetic substitution relatively simple 26-row alphabetical table guaranteeing confidentiality. Machine learning approach Artificial Neural Network (ANN) becomes feasible solution for cryptography by forming secret key in the weight of the network that’s difficult to solve. The key’s generated from bidirectional learning, two parity trees synchronized with hidden neurons, input neurons, and weights. Synchronize public channels by adopting the work of Tree Parity Machine (TPM) with feedforward type. This research utilizes the combination of synchronization ANN and Vigenere from generators. The result of testing the combination of methods doesn’t affect the number of message character and parameter values. The advantages of the resulting key cannot be used repeatedly even though the parameter values ​​are the same, but the key length is the same number of characters. The functionality produces 100% value. Keywords: Cryptography, Artificial Neural Networks (ANN), Tree Parity Machine (TPM), Vigenere Cipher

On the Development of an Optimal Structure of Tree Parity Machine for the Establishment of a Cryptographic Key

When establishing a cryptographic key between two users, the asymmetric cryptography scheme is generally used to send it through an insecure channel. However, given that the algorithms that use this scheme, such as RSA, have already been compromised, it is imperative to research for new methods of establishing a cryptographic key that provide security when they are sent. To solve this problem, a new branch known as neural cryptography was born, using a modified artificial neural network called Tree Parity Machine or TPM. Its purpose is to establish a private key through an insecure channel. This article proposes the analysis of an optimal structure of a TPM network that allows generating and establishing a private cryptographic key of 512-bit length between two authorized parties. To achieve this, the combinations that make possible to generate a key of that length were determined. In more than 15 million simulations that were executed, we measured synchronization times, the number of steps required, and the number of times in which an attacking TPM network manages to imitate the behaviour of the two networks. The simulations resulted in the optimal combination, minimizing the synchronization time and prioritizing security against the attacking network. Finally, the model was validated by applying a heuristic rule.

Notice of Retraction Coupled Tree Parity Machines: Synchronized Secured Session Key based Encryption in Online Transaction

Notice of Retraction-----------------------------------------------------------------------After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of APTIKOM's Publication Principles.We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.The presenting author of this paper has the option to appeal this decision by contacting ij.aptikom@gmail.com.----------------------------------------------------------------------- In this paper, tree parity synchronized session key validation followed by encryption has been proposed for online data communication. Tree Parity Machine transmitting systems at both ends accepted an identical input vector, generated an output bit, validated the weight vector and the networks were trained accordingly based on the output bit which was used to form a protected variable length secret key. Existence of a better degree of coupling between the two topological same tree parity machines has been reflected in this paper. Instead of sharing the entire weight vector, the proposed technique guided the partial transmission and validation of session key. A string of sub key has been derived from the synchronized session key for initial ciphering matrix. The plain text was encrypted through single columnar transposition ciphering at first round of encryption followed by successive cascaded XORing of TPM generated session key. If size of the final block of plain text was less than the size of the key then this block was treated unaltered. Recipient used identical generated session key for performing deciphering process for getting the plain text. Brute force attacks analysis has been implemented which determines a higher amount of time to decrypt by the intruders. Such long computational operations were not feasible by any of randomly selected fast networks at the intruders’ terminals.