Design and FPGA Implementation of a Pseudo-random Number Generator Based on a Hopfield Neural Network Under Electromagnetic Radiation

When implementing a pseudo-random number generator (PRNG) for neural network chaos-based systems on FPGAs, chaotic degradation caused by numerical accuracy constraints can have dramatic impact the performance of PRNG. To suppress this degradation, PRNG with feedback controller based Hopfield oscillator is proposed, in which neuron exposed to electromagnetic radiation. We choose magnetic flux across cell membrane as condition disturb other neurons, thus avoiding periodicity. The proposed modeled and simulated Vivado 2018.3 software implemented synthesized FPGA device ZYNQ-XC7Z020 Xilinx using Verilog HDL code. As basic entropy source, one radiation has been high precision 32-bit Runge Kutta fourth-order method (RK4) algorithm from IEEE 754-1985 floating point standard. post-processing module consists 32 registers 15 XOR comparators. binary data generated scheme was tested analyzed NIST 800.22 statistical test suite. results show that it security randomness. Finally, an image encryption decryption system designed FPGA. feasibility proved simulation analysis.