Wednesday 24th of April 2024
 

Using Layer Recurrent Neural Network to Generate Pseudo Random Number Sequences


Veena Desai, Ravindra Patil and Dandina Rao

Pseudo Random Numbers (PRNs) are required for many cryptographic applications. This paper proposes a new method for generating PRNs using Layer Recurrent Neural Network (LRNN). The proposed technique generates PRNs from the weight matrix obtained from the layer weights of the LRNN. The LRNN random number generator (RNG) uses a short keyword as a seed and generates a long sequence as a pseudo PRN sequence. The number of bits generated in the PRN sequence depends on the number of neurons in the input layer of the LRNN. The generated PRN sequence changes, with a change in the training function of the LRNN .The sequences generated are a function of the keyword, initial state of network and the training function. In our implementation the PRN sequences have been generated using 3 training functions: 1)Scaled Gradient Descent 2)Levenberg-Marquartz (TRAINLM) and 3) TRAINBGF. The generated sequences are tested for randomness using ENT and NIST test suites. The ENT test can be applied for sequences of small size. NIST has 16 tests to test random numbers. The LRNN generated PRNs pass in 11 tests, show no observations for 4 tests, and fail in 1 test when subjected to NIST .This paper presents the test results for random number sequence ranging from 25 bits to 1000 bits, generated using LRNN.

Keywords: Pseudo Random Number Generators, Layer Recurrent Network, ENT ,NIST

Download Full-Text


ABOUT THE AUTHORS

Veena Desai
Veena Desai, received her B.E in Electronics and Communication Engineering form Karnatak University, Dharwad (1991), M.Tech in Computer Network Engineering from Vishvesvarayya Technological University, Belgaum. She has published several papers in national and international conferences. She is presently working as Associate Professor at Gogte Institute of Technology. She has research interest in cryptography, network security and neural networks .She is a graduate student member of IEEE, member ISTE,IETE,CSI,ACM and CRSI.

Ravindra Patil
Ravindra Patil (b. June 06, 1987) received his B.E in Computer Science (2009), M.Tech in Digital Communication and Networking (2011) from Visvesvaraya Technological University, Belgaum.

Dandina Rao
Dr. D.H. Rao has done his Ph.D. in Engineering from University of Saskatchewan, Canada and Ph.D. in Management from University of South Carolina, USA. He has more than 100 research publications in proceedings of international conferences and reputed journals. He has co-authored and edited 3 books. He has traveled extensively across the globe and has chaired and delivered keynote addresses in many international conferences. He has more than 3 decades of academic and research experience. He is presently working as Principal and Director of Jain College of Engineering, Belgaum, India. Prior to joining Jain College of Engineering, he was the Principal of Gogte Institute of Technology, Belgaum, India. His research interests include artificial intelligence, neural networks and context-aware computing. He is a senior member of IEEE and fellow of IETE. He is also a certified NLP (Neuro-Linguistic Programming) Trainer.


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »