Cryptography Based On Neural Network

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.

We present a neural-network approach for computer network security. The approach uses a neural network to learn the decryption and public key creation. It is a new potential source for public key cryptographic schemes which are not based on number theoretic functions, and have small time and memory complexities. The proposed method follows the asymmetric model. While the encryption process and private key creation are based on Boolean algebra, the decryption process is based on a neural network technique. The application of this method shows that the possibility of guessing keys is extremely weaker than using the Data Encryption Standard method (DES), which is a widely-used method of data encryption.

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

The neural network framework used for a development in cryptography. Cryptographic techniques and tools are playing an important role in designing emerging network security technologies. Cryptography is a fundamental part of cryptographic technology and is considered one of the important aspects associated with its use. It is constant battle between cryptographers trying to secure information and cryptanalysts trying to break cryptosystems that moves the entire body of cryptology knowledge forward. Cryptanalysis is the methods for obtaining the meaning of encrypted information, without access to the secret information that is normally required to do so. In this paper we mainly focusing an overview over cryptanalysis and cryptography gives the how neural network application used for this techniques of security mechanisms of cryptography.

International Journal of Advanced Trends in Computer Science and Engineering, 2020

In today's digital world, cryptography became indispensable in almost all trending technologies. For ensuring a completely secure system with limited computational complexity involved in the generation of randomness, secret key and other aspects, researchers employed various techniques to the cryptosystems. Despite the considerable number of strategies, applications of Artificial neural networks (ANN) for cryptographic problems appeared to be more remarkable. Owing to this fact, this work has been devoted to reveal the applications of different kinds of artificial neural networks for different categories in cryptosystems. Artificial Neural Networks are stepping stones in search of artificial intelligence. ANNs are chosen because they are good at generalization, adaptive decision making and unknown pattern recognition. This plethora of information regarding how each neural network was used in different types of cryptosystems is mainly contributed to future researchers to aid their novel works in this discipline. Also, application of Neural networks for cryptography related problems yielded positive results in almost all the applied fields. Therefore, this work is done with the intention of highlighting the novel combination of neural networks and cryptography.

Abstract We present a cryptographic system based on Pollack's recursive auto-associative memory (1991). This self-organizing learning system offers many unique properties not found in traditional crypto systems. This paper examines the methodology and issues of such a system.

Journal of Physics A: Mathematical and General, 2002

Mutual learning process between two parity feed-forward networks with discrete and continuous weights is studied analytically, and we find that the number of steps required to achieve full synchronization between the two networks in the case of discrete weights is finite. The synchronization process is shown to be non-self-averaging and the analytical solution is based on random auxiliary variables. The learning time of an attacker that is trying to imitate one of the networks is examined analytically and is found to be much longer than the synchronization time. Analytical results are found to be in agreement with simulations.

Baghdad Science Journal, 2008

The objective of this work is to design and implement a cryptography system that enables the sender to send message through any channel (even if this channel is insecure) and the receiver to decrypt the received message without allowing any intruder to break the system and extracting the secret information. In this work, we implement an interaction between the feedforward neural network and the stream cipher, so the secret message will be encrypted by unsupervised neural network method in addition to the first encryption process which is performed by the stream cipher method. The security of any cipher system depends on the security of the related keys (that are used by the encryption and the decryption processes) and their corresponding lengths. In our work, there are two types of keys; the first type is the keystream that is adopted by the stream cipher stage with optimal length (length of the keystream greater or equal the message length); and the second key type is the final wei...

Today the world depends on computers and information systems for processing information in various fields. These systems must be developed in such a way that they are less vulnerable to attacks and more reliable and secured. These systems are more vulnerable to technical issues and many cases of data trawling have been reported as a result of password breaches. Encryption and decryption plays a major role in the modern era as the rate of data flow increased tremendously. Social networking sites such as Facebook and Google stores the most important and private data of people electronically in the servers. Artificial intelligence took over many functions of computer systems in different fields including data security. Neural networks process information with care and certainty like human mind does. This paper proposes a methodology to implement encryption and decryption using the feed forward neural networks and to improve the security of information systems.

Journal of Engineering …, 2011

Modern cryptography techniques are virtually unbreakable. As the Internet and other forms of electronic communication become more prevalent, electronic security is becoming increasingly important. Cryptography is used to protect email messages, credit card information, and corporate data. The design of the cryptography system is a conventional cryptography that uses one key for encryption and decryption process. The chosen cryptography algorithm is stream cipher algorithm that encrypt one bit at a time. The central problem in the stream-cipher cryptography is the difficulty of generating a long unpredictable sequence of binary signals from short and random key. Pseudo random number generators (PRNG) have been widely used to construct this key sequence. The pseudo random number generator was designed using the Artificial Neural Networks (ANN). The Artificial Neural Networks (ANN) providing the required nonlinearity properties that increases the randomness statistical properties of the pseudo random generator. The learning algorithm of this neural network is backpropagation learning algorithm. The learning process was done by software program in Matlab (software implementation) to get the efficient weights. Then, the learned neural network was implemented using field programmable gate array (FPGA).