Autoencoder Artificial Neural Network Public Key Cryptography in Unsecure Public channel Communication
Vikas Sagar1, Krishan Kumar2
1Vikas Sagar, Research Scholar, Department of Computer Science Faculty of Technology, Gurukul Kangri University, Haridwar, India.
2Krishan Kumar, Assistant Professor, Department of Computer Science Faculty of Technology, Gurukul Kangri University, Haridwar, India.
Manuscript received on 22 August 2019. | Revised Manuscript received on 03 September 2019. | Manuscript published on 30 September 2019. | PP: 4023-4032 | Volume-8 Issue-11, September 2019. | Retrieval Number: K14560981119/2019©BEIESP | DOI: 10.35940/ijitee.K1456.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: As we all known that cryptography is a procedure to hide data so that it can’t be access or modified by any unauthorized entity. At the present digital world security is a main concern. To maintain this security there are many cryptographic algorithm exist. But the world technology grew each and every day so we have to find some new algorithms to maintain the security at higher level. In the proposed and implemented work used artificial neural network to increase the security during data communication in digital world. Autoencoder Neural Network is a new approach in the era of digital world so that used here in cryptographic algorithm to increase the strength of the security. There are three basic aims of cryptography availability, privacy and integrity easily achieved by this new approach. This work examine that the attacker can’t get access the data however he/she exist in the same network or not. Neural Network’s uncertainty property make this possible. This approach also examined on different data size and key size. Proposed work used the autoencoder for encryption and decryption. The final experimental result show our purposed algorithm efficient and accurate and also show how this approach perform better. Proposed and implemented algorithm can be easily used for secure data communication with more efficiently.
Keywords: Cryptography, Symmetric key, Security, Autoencoder neural network.
Scope of the Article: Cryptography and Applied Mathematics