Searcharxiv⌕ Search

arXiv subjects

Wolfgang Kinzel

Publications and source records attributed to Wolfgang Kinzel.

47 records · Page 3Linked to original sources
arXiv2002

A secure key-exchange protocol with an absence of injective functions

The security of neural cryptography is investigated. A key-exchange protocol over a public channel is studied where the parties exchanging secret messages use multilayer neural networks which are trained by their mutual output bits and synchronize to a time dependent secret key. The weights of the networks have integer values between $\pm L$. Recently an algorithm for an eavesdropper which could break the key was introduced by Shamir et al. [adi]. We show that the synchronization time increases with $L^2$ while the probability to find a successful attacker decreases exponentially with $L$. Hence for large $L$ we find a secure key-exchange protocol which depends neither on number theory nor on injective trapdoor functions used in conventional cryptography.

cond-mat.dis-nn↗
arXiv2002

Theory of Interacting Neural Networks

In this contribution we give an overview over recent work on the theory of interacting neural networks. The model is defined in Section 2. The typical teacher/student scenario is considered in Section 3. A static teacher network is presenting training examples for an adaptive student network. In the case of multilayer networks, the student shows a transition from a symmetric state to specialisation. Neural networks can also generate a time series. Training on time series and predicting it are studied in Section 4. When a network is trained on its own output, it is interacting with itself. Such a scenario has implications on the theory of prediction algorithms, as discussed in Section 5. When a system of networks is trained on its minority decisions, it may be considered as a model for competition in closed markets, see Section 6. In Section 7 we consider two mutually interacting networks. A novel phenomenon is observed: synchronisation by mutual learning. In Section 8 it is shown, how this phenomenon can be applied to cryptography: Generation of a secret key over a public channel.

cond-mat.dis-nn↗
arXiv2002

Interacting neural networks and cryptography

Two neural networks which are trained on their mutual output bits are analysed using methods of statistical physics. The exact solution of the dynamics of the two weight vectors shows a novel phenomenon: The networks synchronize to a state with identical time dependent weights. Extending the models to multilayer networks with discrete weights, it is shown how synchronization by mutual learning can be applied to secret key exchange over a public channel.

cond-mat.dis-nn↗
arXiv2002

Learning and predicting time series by neural networks

Artificial neural networks which are trained on a time series are supposed to achieve two abilities: firstly to predict the series many time steps ahead and secondly to learn the rule which has produced the series. It is shown that prediction and learning are not necessarily related to each other. Chaotic sequences can be learned but not predicted while quasiperiodic sequences can be well predicted but not learned.

cond-mat.dis-nn↗
arXiv2002

Cryptography based on neural networks - analytical results

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.

cond-mat.stat-mech↗
arXiv2001

Generation of unpredictable time series by a Neural Network

A perceptron that learns the opposite of its own output is used to generate a time series. We analyse properties of the weight vector and the generated sequence, like the cycle length and the probability distribution of generated sequences. A remarkable suppression of the autocorrelation function is explained, and connections to the Bernasconi model are discussed. If a continuous transfer function is used, the system displays chaotic and intermittent behaviour, with the product of the learning rate and amplification as a control parameter.

cond-mat.dis-nn↗
arXiv2000

Multi-Choice Minority Game

The generalization of the problem of adaptive competition, known as the minority game, to the case of $K$ possible choices for each player is addressed, and applied to a system of interacting perceptrons with input and output units of the type of $K$-states Potts-spins. An optimal solution of this minority game as well as the dynamic evolution of the adaptive strategies of the players are solved analytically for a general $K$ and compared with numerical simulations.

cond-mat.dis-nn↗
arXiv2000

A lattice gas model of II-VI(001) semiconductor surfaces

We introduce an anisotropic two-dimensional lattice gas model of metal terminated II-IV(001) seminconductor surfaces. Important properties of this class of materials are represented by effective NN and NNN interactions, which result in the competition of two vacancy structures on the surface. We demonstrate that the experimentally observed c(2x2)-(2x1) transition of the CdTe(001) surface can be understood as a phase transition in thermal equilbrium. The model is studied by means of transfer matrix and Monte Carlo techniques. The analysis shows that the small energy difference of the competing reconstructions determines to a large extent the nature of the different phases. Possible implications for further experimental research are discussed.

cond-mat.stat-mech↗
arXiv1997

Modeling sublimation by computer simulation: morphology dependent effective energies

Solid-On-Solid (SOS) computer simulations are employed to investigate the sublimation of surfaces. We distinguish three sublimation regimes: layer-by-layer sublimation, free step flow and hindered step flow. The sublimation regime is selected by the morphology i.e. the terrace width. To each regime corresponds another effective energy. We propose a systematic way to derive microscopic parameters from effective energies and apply this microscopical analysis to the layer-by-layer and the free step flow regime. We adopt analytical calculations from Pimpinelli and Villain and apply them to our model. Key-Words: Computer simulations; Models of surface kinetics; Evaporation and Sublimation; Growth; Surface Diffusion; Surface structure, morphology, roughness, and topography; Cadmium telluride

cond-mat↗
arXiv1997

Phase Transitions of Neural Networks

The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.

cond-mat.dis-nn↗