Cryptography based on neural networks analytical results

ECMS 2012 Proceedings edited by: K. G. Troitzsch, M. Moehring, U. Lotzmann, 2012

The goal of cryptography is to make it impossible to take a cipher and reproduce the original plain text without the corresponding key. With good cryptography, your messages are encrypted in such a way that brute force attacks against the algorithm or the key are all but impossible. Good cryptography gets its security by using incredibly long keys and using encryption algorithms that are resistant to other form attack. The neural net application represents a way of the next development in good cryptography. This paper deals with using neural network in cryptography, e.g. designing such neural network that would be practically used in the area of cryptography. This paper also includes an experimental demonstration.

Physical review. E, Statistical, nonlinear, and soft matter physics, 2002

Mutual learning of a pair of tree parity machines with continuous and discrete weight vectors is studied analytically. The analysis is based on a mapping procedure that maps the mutual learning in tree parity machines onto mutual learning in noisy perceptrons. The stationary solution of the mutual learning in the case of continuous tree parity machines depends on the learning rate where a phase transition from partial to full synchronization is observed. In the discrete case the learning process is based on a finite increment and a full synchronized state is achieved in a finite number of steps. The synchronization of discrete parity machines is introduced in order to construct an ephemeral key-exchange protocol. The dynamic learning of a third tree parity machine (an attacker) that tries to imitate one of the two machines while the two still update their weight vectors is also analyzed. In particular, the synchronization times of the naive attacker and the flipping attacker recentl...

Cryptography is the one of the main categories of computer security that converts information from its normal form into an unreadable form. An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, Neural Network (NN) has emerged over the years and has made remarkable contribution to the advancement of various fields of endeavor. The purpose of this paper is to using neural networks on Cryptography , In this paper also, we have examined and analyzed the various architectures of NN.

IEEE Access

A current trend of research focuses on artificial intelligence based cryptography which although proposed almost thirty years ago could not attract much attention. Abadi and Anderson's work on adversarial cryptography in 2016 rejuvenated the research area which now focuses in building neural networks that are able to learn cryptography using the idea from Generative Adversarial Networks (GANs). In this paper, we survey the most prominent research works that cover neural networks based cryptography from two main periods. The first period covers the oldest models that have been proposed shortly after 2000 and the second period covers the more recent models that have been proposed since 2016. We first discuss the implementation of the systems from the earlier era and the attacks mounted on them. After that, we focus on post 2016 era where more advanced techniques are utilized that rely on GANs in which neural networks compete with each other in order to achieve a goal e.g. learning to encrypt a communication. Finally, we discuss security analysis performed on adversarial cryptography models. INDEX TERMS cryptography, deep learning, neural networks, generative adversarial networks

International Journal of Computer Applications, 2016

Cryptography is a skill of sending the data in such a form that only those for whom it is intended can read it. There are number of methods to perform cryptography, one of such methods is Chaos theory which studies the behavior of a dynamical systems that are highly sensitive to initial conditions. Even slight changes in initial conditions result in extensively deviating outcomes for such dynamical systems, hence making long-standing estimate unmanageable. The limitations of applying Chaos Theory are choosing the input parameters and synchronization. The computation of these input parameters lies on the dynamics underlying the data and the highly complex analysis, not always accurate. Artificial neural networks (ANN) well known for learning and generalization are hence used to model the dynamics of Chua's circuit viz. x, y and z. The designed ANN was trained by varying its structures and using different learning algorithms. ANN was trained using 9 different sets which were formed with the initial conditions of Chua's circuit and each set consisted of about 1700 input-output data. A feedforward Multi-Layer Perceptron (MLP) network structure, trained with Levenberg-Marquardt backpropagation algorithm, produced best outcome. Further a case study in which a plain text was first encoded and then decoded by both the chaotic dynamics obtained from the proposed ANN and the numerical solution of Chua's circuit and are compared with each other.

2014

In this paper a new hash function is constructed based on multilayer feed forward network with piecewise linear chaotic map. Chaos has been used in data protection because of the features of initial value sensitivity, random similarity and ergodicity. We have used three neuronal layers to prove confusion, diffusion and compression respectively. This hash function takes input of arbitrary length and generate a fixed length hash value.(128 bit, 256 bit or 512 bit). By performance analysis and results we have shown that generated hash function is one way, collision resistant and secure against birthday attacks and man in middle attacks. Keywords—Neural Network, Cryptography, Tree parity machines, Piecewise linear chaotic map, hash function, plain text sensitivity, data signature

Cryptography is the ability of changing information into obvious unintelligibility in a way allowing a secret method of un-mangling. The vital idea of cryptography is the capability to send information between participants in a way that prevents others from reading it. Much cryptography methods are available which are based on number theory but it has the disadvantage of requirement a large computational power, complexity and time consumption. To overcome these drawbacks, artificial neural networks (ANNs) have been applied to solve many problems. The ANNs have many characteristics such as learning, generalization, less data requirement, fast computation, ease of implementation, and software and hardware availability, which make it very attractive for many applications. This paper provides a stateof-the-art review on the use of artificial neural networks in cryptography and studies their performance on approximation problems related to cryptography.

2005 Annual IEEE India Conference - Indicon

Information protection is now a crucial problem and good solution to this problem is cryptography and steganography. The content of message is kept secret in cryptography, where as in Steganography; a message is embedded in a cover image. In our proposed work a system is developed in which LSB Steganography and Cryptography using chaotic neural network is combined together to provide high security to the message during communication in an unsecure channel. In LSB Steganography taking advantage of the way the human eye perceives images, the technique involves of replacing the N least significant bits of each pixel of a container image with the data of a hidden message. Cryptography based on chaotic neural network is used because of its noise like behaviour which is quite significant for cryptanalyst to know about the hidden information as it is hard to predict. Thus the information is being kept secret. In this work we have considered the advantages of both the concepts and developed a model in which initially a message is embedded in a gray scale image using LSB steganography and then the stegoimage is encrypted using chaotic neural network to provide high security to the message. The whole process is implemented using MATLAB. The simulation results show the robustness of the technique.

In the recent years there has been quite a development in the field of artificial intelligence one of which has been the introduction of the artificial neural networks (ANN). The ANN can be considered as an information processing unit which to a great extent resembles the working of the human brain. Its utilization has spread through various fields namely bioinformatics, stock market predictions, medical science, weather forecasting etc. One of these fields in which ANN has been indispensable is cryptography. Recently there has been quite a study going on various encryption methods based on neural nets comprising of single layer or multilayer perceptron models. This field of cryptography is more popularly known as Neural Cryptography. The learning method of ANN architecture can be well utilized to generate more effective encryption systems based on feedback. In the present paper the authors tried to make a theoretical study on how ANN can be used in data encryption.

Neural Networks, 2009. IJCNN 2009. …, 2009

Neural cryptography deals with the problem of key exchange using the mutual learning concept between two neural networks. The two networks will exchange their outputs (in bits) so that the key between the two communicating parties is eventually represented in the final learned weights and the two networks are said to be synchronized. Security of neural synchronization depends on the probability that an attacker can synchronize with any of the two parties during the training process, so decreasing this probability improves the reliability of exchanging their output bits through a public channel. This work proposes an exchange technique that will disrupt the attacker confidence in the exchanged outputs during training. The algorithm is based on one party sending erroneous output bits with the other party being capable of predicting and removing this error. The proposed approach is shown to outperform the synchronization with feedback algorithm in the time needed for the parties to synchronize.