Chaotic multimedia stream cipher scheme based on true random sequence combined with tree parity machine

Pu, Xin; Tian, Xuemin; Zhang, Jing; Liu, Chunyan; Yin, Jing

doi:10.1007/s11042-016-3728-0

Cited by 10 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The timing distribution of the two TPM networks is adapted from the Poisson distribution by Dolecki and Kozera [27]. Pu et al [28] developed an algorithm that blends ''true random sequences'' with a TPM network that demonstrates more complex dynamic behaviors that increase the efficiency of encryption and resistance to attacks. According to their study, the synaptic weight values of the TPM networks are generated in a secure, standardized, and distributed.…”

Section: Related Workmentioning

confidence: 99%

Artificial Neural Synchronization Using Nature Inspired Whale Optimization

et al. 2021

View full text Add to dashboard Cite

In this article, a whale optimization-based neural synchronization has been proposed for the development of the key exchange protocol. At the time of exchange of sensitive information, intruders can effortlessly perform sniffing, spoofing, phishing, or Man-In-The-Middle (MITM) attack to tamper the vital information. Information needs to be secretly transmitted with high level of encryption by preserving the authentication, confidentiality, and integrity factors. Such stated requirements urge the researchers to develop a neural network-based fast and robust security protocol. A special neural network structure called Double Layer Tree Parity Machine (DLTPM) is proposed for neural synchronization. Two DLTPMs accept the common input and different weight vectors and update the weights using neural learning rules by exchanging their output. In some steps, it results in complete synchronization, and the weights of the two DLTMs become identical. These identical weights serve as a secret key. There is, however, hardly any research in the field of neural weight vector optimization using a nature-inspired algorithm for faster neural synchronization. In this article, whale optimization-based DLTPM is proposed. For faster synchronization, this proposed DLTPM model uses a whale algorithm optimized weight vector. This proposed DLTPM model is faster and has better security. This proposed technique has been passed through a series of parametric tests. The results have been compared with some recent techniques. The results of the proposed technique have shown effective and has robust potential.The associate editor coordinating the review of this manuscript and approving it for publication was Jiafeng Xie.secret while he may be able to follow the structure of the algorithm. Chen et al. [2]; Liu et al. [3]; Chen et al. [4]; Wang et al. [5], [6]; Xiao et al. [7]; Zhang and Cao [8]; Wang et al. [9]; Dong et al. [10] described that the neural network synchronization approach offers the chance to solve enormous exchange problems. Rosen-Zvi et al. [11]; Lakshmanan et al. [12] ; Ni and Paul [13] recently showed that neural cryptography has the capability of achieving key exchange through neural synchronization of Artificial Neural Networks (ANN). This proposed technique uses an ANN called the Double Layer Tree Parity Machine (DLTPM). By generating common inputs and sharing the outputs of such networks,

show abstract

Section: Related Workmentioning

confidence: 99%

Artificial Neural Synchronization Using Nature Inspired Whale Optimization

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As a result, the random weight's replacement with optimum weights decreases the time of synchronization. Pu et al [39] carry out an algorithm, which combines "true random sequences" with a TPM network that shows more complex dynamic behaviors which enhances encryption efficiency and attack resistance. According to the analysis, a safe, uniform and distribution for the synaptic weight values of the TPM networks are produced.…”

Section: Related Workmentioning

confidence: 99%

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

Sarkar

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Neural synchronization is a technique for establishing the cryptographic key exchange protocol over a public channel. Two neural networks receive common inputs and exchange their outputs. In some steps, it leads to full synchronization by setting the discrete weights according to the specific rule of learning. This synchronized weight is used as a common secret session key. But there are seldom research is done to investigate the synchronization of a cluster of neural networks. In this paper, a Generative Adversarial Network (GAN)-based synchronization of a cluster of neural networks with three hidden layers is proposed for the development of the public-key exchange protocol. This paper highlights a variety of interesting improvements to traditional GAN architecture. Here GAN is used for Pseudo-Random Number Generators (PRNG) for neural synchronization. Each neural network is considered as a node of a binary tree framework. When both i-th and j-th nodes of the binary tree are synchronized then one of these two nodes is elected as a leader. Now, this leader node will synchronize with the leader of the other branch. After completion of this process synchronized weight becomes the session key for the whole cluster. This proposed technique has several advantages like (1) There is no need to synchronize one neural network to every other in the cluster instead of that entire cluster can be able to share the same secret key by synchronizing between the elected leader nodes with only logarithmic synchronization steps. (2) This proposed technology provides GAN-based PRNG which is very sensitive to the initial seed value. (3) Three hidden layers leads to the complex internal architecture of the Tree Parity Machine (TPM). So, it will be difficult for the attacker to guess the internal architecture. (4) An increase in the weight range of the neural network increases the complexity of a successful attack exponentially but the effort to build the neural key decreases over the polynomial time. (5) The proposed technique also offers synchronization and authentication steps in parallel. It is difficult for the attacker to distinguish between synchronization and authentication steps. This proposed technique has been passed through different parametric tests. Simulations of the process show effectiveness in terms of cited results in the paper.

show abstract

“…Moreover, with increase in the number of input and hidden neurons, the chances of counterfeiting the “Majority Flip Attacks” were also made high. Pu et al [ 51 ] had developed an algorithm that deals with true random sequences, generated through artificial neural networks and TPM networks. It had shown larger complex dynamic perspectives in terms of a better placed encryption tool.…”

Section: Literature Surveymentioning

confidence: 99%

ICT-Guided Glycemic Information Sharing Through Artificial Neural Telecare Network

Dey¹,

Sarkar

Karforma

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

The revolutionary and retrospective changes in the use of ICT have propelled the introduction of telecare health services in the crucial corona virus pandemic times. There have been revolutionary changes that happened with the advent of this novel corona virus. The proposed technique is based on secured glycemic information sharing between the server and users using artificial neural computational learning suite. Using symmetric Tree Parity Machines (TPMs) at the server and user ends, salp swarm-based session key has been generated for the proposed glycemic information modular encryption. The added taste of this paper is that without exchanging the entire session key, both TPMs will get full synchronized in terms of their weight vectors. With rise in the intake of highly rated Glycemic Indexed (GI) foods in today’s COVID-19 lockdown lifestyle, it contributes a lot in the formation of cavities inside the periodontium, and several other diseases likes of COPD, Type I and Type II DM. GI-based food pyramid depicts the merit of the food in the top to bottom spread up approach. High GI food items helps in more co-morbid diseases in patients. It is recommended to have foods from the lower radars of the food pyramid. The proposed encryption with salp swarm-generated key has been more resistant to Man-In-The-Middle attacks. Different mathematical tests were carried on this proposed technique. The outcomes of those tests have proved its efficacy, an acceptance of the proposed technique. The total cryptographic time observed on four GI modules was 0.956 ms, 0.468 ms, 0.643 ms, and 0.771 ms.

show abstract

Chaotic multimedia stream cipher scheme based on true random sequence combined with tree parity machine

Cited by 10 publications

References 20 publications

Artificial Neural Synchronization Using Nature Inspired Whale Optimization

Artificial Neural Synchronization Using Nature Inspired Whale Optimization

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

ICT-Guided Glycemic Information Sharing Through Artificial Neural Telecare Network

Contact Info

Product

Resources

About