Combination of biometric data and learning algorithms for both generation and application of a secure communication link

Authors:
Dirk Neumann;Rolf Eckmiller;Oliver Baruth
Affiliations:
Division of Neural Computation, Department of Computer Science, University of Bonn, Roemerstr. 164, 53117 Bonn, Germany. Tel.: +49 228 73 4422/ Fax: +49 228 73 4425/ E-mail: {neumann,eckmiller,bar ...;(Correspd. eckmiller@nero.uni-bonn.de) Division of Neural Computation, Department of Computer Science, University of Bonn, Roemerstr. 164, 53117 Bonn, Germany. Tel.: +49 228 73 4422/ Fax: +49 228 ...;Division of Neural Computation, Department of Computer Science, University of Bonn, Roemerstr. 164, 53117 Bonn, Germany. Tel.: +49 228 73 4422/ Fax: +49 228 73 4425/ E-mail: {neumann,eckmiller,bar ...
Venue:
Integrated Computer-Aided Engineering - Artificial Neural Networks
Year:
2007

Citing 11
Cited 2

Adaptive filter theory (2nd ed.)

Adaptive filter theory (2nd ed.)
Applied cryptography (2nd ed.): protocols, algorithms, and source code in C

Applied cryptography (2nd ed.): protocols, algorithms, and source code in C
Cryptography and Network Security: Principles and Practice

Cryptography and Network Security: Principles and Practice
Cryptography Efficient Permutation Instructions for Fast Software

IEEE Micro
Automatic Fingerprint Recognition Systems

Automatic Fingerprint Recognition Systems
Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)

Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)
Security on FPGAs: State-of-the-art implementations and attacks

ACM Transactions on Embedded Computing Systems (TECS)
On-Chip Lookup Tables for Fast Symmetric-Key Encryption

ASAP '05 Proceedings of the 2005 IEEE International Conference on Application-Specific Systems, Architecture Processors
Development of a neural net-based, personalized secure communication link

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
On optimal permutation codes

IEEE Transactions on Information Theory
Filterbank-based fingerprint matching

IEEE Transactions on Image Processing

A probabilistic neural network for earthquake magnitude prediction

Neural Networks
The multi-bit watermarking method for speech signals in the time-frequency domain

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a novel secure communication system (SCS) via public networks. For the generation of a unique pair of encryption module (EM) and decryption module (DM), learning algorithms are applied in combination with biometric data of the future DM-user. Subsequently, EM can be attached to any computer to form a generally usable encryption unit (EU) while DM, if attached to another computer to form the matching decryption unit (DU), can only be activated by the specific pair-generating DM-user. EU transforms spatial data to temporal data by means of spatio-temporal (ST) filters. DU uses a combination of analytical- and learning algorithms for decryption.