A New Technique on Neural Cryptography with Securing of Electronic Medical Records in Telemedicine System

摘要

There is a necessity to secure the Electronic Medical Records (EMR) when the exchange of medical information is taken place among the patients and doctors. We can generate a common secret key using neural networks and cryptography. Two neural networks which are trained on their mutual output bits are analyzed using methods of statistical physics. In the proposed Tree Parity Machines (TPMs), hidden layer of each output vectors are compared. That is, the output vectors of hidden unit using Hebbian learning rule, left-dynamic hidden unit using Random walk learning rule and right-dynamic hidden unit using Anti-Hebbian learning rule are compared. Among the compared values, one of the best values is received by the output layer. Similarly, the other hidden units, left-dynamic hidden units and right-dynamic hidden units perform the same operations and values are received by the output layer. The output layer receives the inputs from the hidden layer and then calculates the weights using different transfer functions, which reduce the feedback mechanism because each output is compared. Then the best compared weight is updated in the output unit. The EMR is compressed using Huffman compression, the CEMR (Compressed EMR) which is based on password-protection from the combination of lower layer’s spy unit vector and upper layer’s spy unit vector. A network with feedback generates a secret key, which can be used to encrypt and decrypt the CEMR using Rijndael Algorithm. Also, the timing to break a secret key using brute force attack is also explained in this study.