Key Identifications Using Hebbian Learning
The increasing threat to data over public channels has bought about a need to secure sensitive data to avoid its misuse and tampering. This makes data security an important issue in the present which will continue to pose a problem in the future.
Over the successive years a lot of work has been done in this field, with the recent developments focusing on neural networks and its application in security. Neural network algorithms for the same like Multilayer Perceptron technique, Back Propagation Technique have been implemented. Multilayer Perceptron technique aforesaid model lacks in accuracy and is complex whereas the Back Propagation Technique is more accurate but its complexity is more than Multilayer Perceptron and also has result convergence faults.
This paper deals with data encryption using a random set of keys and the key identification using Hebbian learning. Here bits of data are taken at a time and encrypted using a key from given set of keys. The key is identified using Hebbian learning and hence data is decrypted. Main advantage of this method is its simplicity and that it is error free in lossless transmission.
KeywordsNeural network Hebbian learning Key identification Hebbian learning for key identification
- 1.Luo, B., Liu, Y.: The risk evaluation model of network information security based on improved BP neural network. IEEE (2012)Google Scholar
- 2.Fu, J., Huang, L., Yao, Y.: Application of BP neural network in wireless network security evaluation. IEEE (2010)Google Scholar
- 4.El-Sharkawi, M.A., Huang, S.J.: Development of genetic algorithm embedded Kohonen neural network for dynamic security assessment. IEEE (1996)Google Scholar
- 5.Risk modelling (2010). http://www.owasp.org/index.php/Threat_Risk_Modeling. Accessed 24 Sep 2014
- 6.Dengguo, F., Yang, Z., Yuqing, Z.: Risk assessment of information security survey. J. China Inst. Commun. 25(7), 10–18 (2004)Google Scholar
- 7.Liming, Z.: Artificial Neural Network Model and Its Application. Fudan University Press, Shanghai (1994)Google Scholar
- 8.Salek, Z., Madani, F.M., Azmi, R.: Intrusion detection using neural networks trained by differential evaluation algorithmGoogle Scholar