Using Artificial Neural Networking in Cryptography
Cryptography system helps in transformation of information among authenticated users where there is no involvement of any third party using that information without that information with unauthorized access. This project implements encryption and decryption using neural network cryptography using AES key. The network construction will be generated solely on the parameters used in the training algorithm and the number of hidden neurons. In neural cryptography, both the communicating networks would receive an identical input vector(s), generate an output bit and are trained based on the output bit, the networks are to be synchronize to a state with identical time-dependent weights. This concept of synchronization by mutual learning can be applied to a secret key exchange protocol over a public channel which would be further used in cryptography. Earlier generation of secret key over a public channel used for encrypting and decrypting the given message using DES algorithm in neural cryptography was widely adopted. But, In this project we would using AES algorithm for key generation in neural cryptography. AES algorithm replaces the small key size generated by DES and also the Triple DES as it founds to be six times faster.
Keywords: Neural networks, cryptography, key generation, Tree Parity machine, Security Attacks
Cite this Article: Himani Dua, Abhay Shukla. Using Artificial Neural Networking in Cryptography. Journal of Artificial Intelligence Research & Advances. 2020; 7(2): 56–61p.
- There are currently no refbacks.
This site has been shifted to https://stmcomputers.stmjournals.com/