Two-layer tree-connected feed-forward neural network model for neural cryptography

Lei, Xinyu; Liao, Xiaofeng; Chen, Fei; Huang, Tingwen

doi:10.1103/physreve.87.032811

Cited by 11 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN model applies a learning algorithm for nonlinear statistical data modeling by mimicking the way nerve cells work in the human brain, and the model is particularly efficient in implicitly estimating complex nonlinear relationships between input features and target predictions 86 . We choose a single layer feed-forward neural network consisting of an input layer, hidden layer, and output layer [87][88][89] . The input is the pore structural features, and effective reaction rates from pore-scale simulations are the target predictions.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Machine Learning to Predict Effective Reaction Rates in 3D Porous Media From Pore Structural Features

Liu

Kwon

Kang

2022

Preprint

View full text Add to dashboard Cite

Large discrepancies between well-mixed reaction rates and effective reactions rates estimated under fluid flow conditions have been a major issue for predicting reactive transport in porous media systems. In this study, we introduce a framework that accurately predicts effective reaction rates directly from pore structural features by combining 3D pore-scale numerical simulations with machine learning (ML). We first perform pore-scale reactive transport simulations with fluid-solid reactions in hundreds of porous media and calculate effective reaction rates from pore-scale concentration fields. We then train a Random Forests model with 11 pore structural features and effective reaction rates to quantify the importance of structural features in determining effective reaction rates. Based on the importance information, we train artificial neural networks with varying number of features and demonstrate that effective reaction rates can be accurately predicted with only three pore structural features, which are specific surface, pore sphericity, and coordination number. Finally, global sensitivity analyses using the ML model elucidates how the three structural features affect effective reaction rates. The proposed framework enables accurate predictions of effective reaction rates directly from a few measurable pore structural features, and the framework is readily applicable to a wide range of applications involving porous media flows.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Machine Learning to Predict Effective Reaction Rates in 3D Porous Media From Pore Structural Features

Liu

Kwon

Kang

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…With respect to the proposed algorithms for the design of the TPM network, Lei et al [13] developed a two-layer, prepowered TPM network model. A fast synchronization can be achieved by increasing the minimum value of the internal representations Hamming distance and by reducing the probability of a step that does not modify networks weights.…”

Section: Related Workmentioning

confidence: 99%

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

Dorokhin

Fuertes

Lascano

2019

Security and Communication Networks

View full text Add to dashboard Cite

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.

show abstract

“…As research in this field progressed, a general consensus started emerging that, till now, the tree parity machine (TPM) network with hidden unit K=3 is the model that is most suitable for a neural protocol [28]. Thus, it becomes important to find more variety of neural network architectures and synchronizing mechanisms that provide enhanced security to different forms of attacks.…”

Section: Other Recent Studiesmentioning

confidence: 99%

“…Thus, in 2013, a two-layer tree-connected feed-forward neural network (TTFNN) model was proposed. This model utilized the concept that two communicating partners are capable of exchanging a vector with multiple bits in each time step [28]. In this work, feasible conditions and heuristic rules that would make the neural synchronization based protocol successful against common attacks were obtained.…”

Section: Other Recent Studiesmentioning

confidence: 99%

Neural synchronization based secret key exchange over public channels: A survey

Chakraborty¹,

Dalal²,

Sarkar³

et al. 2014

2014 International Conference on Signal Propagation and Computer Technology (ICSPCT 2014)

View full text Add to dashboard Cite

Abstract-Exchange of secret keys over public channels based on neural synchronization using a variety of learning rules offer an appealing alternative to number theory based cryptography algorithms. Though several forms of attacks are possible on this neural protocol e.g. geometric, genetic and majority attacks, our survey finds that deterministic algorithms that synchronize with the end-point networks have high time complexity, while probabilistic and population-based algorithms have demonstrated ability to decode the key during its exchange over the public channels. Our survey also discusses queries, heuristics, erroneous information, group key exchange, synaptic depths, etc, that have been proposed to increase the time complexity of algorithmic interception or decoding of the key during exchange. The Tree Parity Machine and its variants, neural networks with tree topologies incorporating parity checking of state bits, appear to be one of the most secure and stable models of the end-point networks. Our survey also mentions some noteworthy studies on neural networks applied to other necessary aspects of cryptography. We conclude that discovery of neural architectures with very high synchronization speed, and designing the encoding and entropy of the information exchanged during mutual learning, and design of extremely sensitive chaotic maps for transformation of synchronized states of the networks to chaotic encryption keys, are the primary issues in this field.

show abstract

Two-layer tree-connected feed-forward neural network model for neural cryptography

Cited by 11 publications

References 29 publications

Machine Learning to Predict Effective Reaction Rates in 3D Porous Media From Pore Structural Features

Machine Learning to Predict Effective Reaction Rates in 3D Porous Media From Pore Structural Features

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

Neural synchronization based secret key exchange over public channels: A survey

Contact Info

Product

Resources

About