scholarly journals Multilayer Perceptron Guided Key Generation through Mutation with Recursive Replacement in Wireless Communication (MLPKG)

2012 ◽  
Vol 2 (3) ◽  
pp. 11-28 ◽  
Author(s):  
Arindam Sarkar
Keyword(s):  
Wireless Communication ◽  
Multilayer Perceptron ◽  
Key Generation

scholarly journals Multilayer neural network synchronized secured session key based encryption in wireless communication

2019 ◽  
Vol 14 (1) ◽  
pp. 169 ◽  
Author(s):  
Arindam Sarkar ◽  
Joydeep Dey ◽  
Anirban Bhowmik
Keyword(s):  
Neural Network ◽  
Wireless Communication ◽  
Frequency Analysis ◽  
Multilayer Perceptron ◽  
Secret Key ◽  
Session Key ◽  
Novel Approach ◽  
Layered Networks ◽  
Hidden Layer ◽  
Energy Computation

<p>Energy computation concept of multilayer neural network synchronized on derived transmission key based encryption system has been proposed for wireless transactions. Multilayer perceptron transmitting machines accepted same input array, which in turn generate a resultant bit and the networks were trained accordingly to form a protected variable length secret-key. For each session, different hidden layer of multilayer neural network is selected randomly and weights of hidden units of this selected hidden layer help to form a secret session key. A novel approach to generate a transmission key has been explained in this proposed methodology. The last thirty two bits of the session key were taken into consideration to construct the transmission key. Inverse operations were carried out by the destination perceptron to decipher the data. Floating frequency analysis of the proposed encrypted stream of bits has yielded better degree of security results. Energy computation of the processed nodes inside multi layered networks can be done using this proposed frame of work.</p>

scholarly journals Multilayer neural network synchronized secured session key based encryption in wireless communication

2019 ◽  
Vol 8 (1) ◽  
pp. 44 ◽  
Author(s):  
Arindam Sarkar
Keyword(s):  
Neural Network ◽  
Wireless Communication ◽  
Multilayer Perceptron ◽  
Secret Key ◽  
Session Key ◽  
Chi Square ◽  
Plain Text ◽  
Chi Square Test ◽  
Hidden Layer ◽  
Final Block

In this paper, multilayer neural network synchronized session key based encryption has been proposed for wireless communication of data/information. Multilayer perceptron transmitting systems at both ends accept an identical input vector, generate an output bit and the network are trained based on the output bit which is used to form a protected variable length secret-key. For each session, different hidden layer of multilayer neural network is selected randomly and weights or hidden units of this selected hidden layer help to form a secret session key. The plain text is encrypted through chaining , cascaded xoring of multilayer perceptron generated session key. If size of the final block of plain  text is less than the size of the key then this block is kept unaltered.  Receiver will use identical multilayer perceptron generated session key for performing deciphering process for getting the plain text. Parametric tests have been  done and results are compared in terms of Chi-Square test, response time in transmission with some existing classical techniques, which shows comparable results for the proposed technique.

Particle Swarm Optimization-Based Session Key Generation for Wireless Communication (PSOSKG)

2015 ◽  
pp. 640-677 ◽  
Author(s):  
Arindam Sarkar ◽  
Jyotsna Kumar Mandal
Keyword(s):  
Particle Swarm Optimization ◽  
Wireless Communication ◽  
Velocity Vector ◽  
Particle Swarm ◽  
Threshold Value ◽  
Key Generation ◽  
Session Key ◽  
Swarm Optimization ◽  
Minimum Probability ◽  
Velocity Level

In this chapter, a Particle Swarm Optimization-Based Session Key Generation for wireless communication (PSOSKG) is proposed. This cryptographic technique is solely based on the behavior of the particle swarm. Here, particle and velocity vector are formed for generation of keystream by setting up the maximum dimension of each particle and velocity vector. Each particle position and probability value is evaluated. Probability value of each particle can be determined by dividing the position of a particular particle by its length. If probability value of a particle is less than minimum probability value then a velocity is applied to move each particle into a new position. After that, the probability value of the particle at the new position is calculated. A threshold value is selected to evaluate against the velocity level of each particle. The particle having the highest velocity more than predefined threshold value is selected as a keystream for encryption.

Sign in / Sign up

Export Citation Format

Share Document