Multi-Party Security System using Artificial Neural Networks

Urvashi Rahul Saxena (JSS Academy of Technical Education.Noida(U.P))
S.P Singh (Birla Institute of Technology,Noida)

IAES International Journal of Artificial Intelligence (IJ-AI)
Vol 1, No 3: September 2012

Multi-Party Security System is an improvised version of various security systems available using Artificial Neural Networks (ANN’s) as an Intelligent Agent for Intrusion Detection. This Paper focuses how inputs can be preserved to serve as a measure for securing communication protocol between two parties using privacy protocols at the hidden layer of Multi-layer Perceptron model. Various neural network structures are observed for evaluating the optimal network considering the number of hidden layers. Results depict that the generated system is capable of classifying records with about 90% of accuracy when two hidden layers are engulfed and the accuracy reduces to 87% with one hidden layer under observation.DOI: http://dx.doi.org/10.11591/ij-ai.v1i3.739