We have been developing an efficient and scalable technique for computer network security by encrypting the text using Boolean algebra and decrypting the encrypted text using neural network. The encryption scheme and the private key creation process are based on Boolean algebra and the decryption scheme and the public key creation are based on a multi-layer neural network that is trained by backpropagation learning algorithm. This is a new potential source for public key cryptographic schemes as latest trends through neural networks. The functions have small time and memory complexities. The test results are also shown that the possibility of guessing keys is extremely weaker than using the Data Encryption Standard method (DES), which is a most widely-used method of data encryption.
Decryption, backpropagation, encryption, multi layer feed forward, neural networks, neuron, private key, public key
