A dual artificial neural network core PRNG on FPGA driven by a novel 4D hyperchaotic system with hidden attractor

This paper introduces a hardware-implemented pseudo-random number generator (PRNG) driven by a constructed Novel 4D Hyperchaotic System with Hidden Attractors (N4DHSHA). The dynamical properties of the oscillator are rigorously investigated through Lyapunov exponent spectra, bifurcation diagrams, basins of attraction, and the 0–1 test for chaos, revealing a Maximal Lyapunov Exponent (MLE) of 4.4662 alongside robust multistability. Furthermore, the model demonstrates linear topological controllability via DC offset boosting and amplitude scaling. To resolve the challenge of digitizing delicate equilibrium-free attractors, we propose a dual Artificial Neural Network (ANN) core architecture consisting of a Predictor layer activated by a Log-Sigmoid function and a Refiner layer activated by a Hyperbolic Tangent Sigmoid function. The proposed generator is implemented on a Xilinx Virtex-6 FPGA utilizing the 32-bit IEEE-754 floating-point standard. By harvesting 18-bit Least Significant Bit slices per clock cycle, the system achieves a real-time throughput of 139.714 Mbps at a 139.714 MHz operating frequency. Post-synthesis evaluations indicate highly optimized hardware footprint metrics, consuming 63.69% of available slice registers and 3.13% of DSP48E1 slices. The statistical verification shows that the generated bitstreams pass all 16 sub-tests of the NIST SP 800 − 22 test suite with P-values exceeding 0.01, proving that the dual-core neural architecture successfully preserves hyperchaotic complexity to deliver an entropy source for secure communications and image encryption.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-13
DOI
https://doi.org/10.1038/s41598-026-79716-3
Primary Topic
Chaos-based Image/Signal Encryption
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A dual artificial neural network core PRNG on FPGA driven by a novel 4D hyperchaotic system with hidden attractor

Khaled Benkouider, Murat Alçın, Mokhairi Makhtar, Sundarapandian V. Vaidyanathan et al.
1 links
Scientific Reports
Chaos-based Image/Signal Encryption
article

A dual artificial neural network core PRNG on FPGA driven by a novel 4D hyperchaotic system with hidden attractor

Khaled Benkouider, Murat Alçın, Mokhairi Makhtar, Sundarapandian V. Vaidyanathan, Aceng Sambas, Murat Tuna, İsmail Koyuncu, Abdulgader Zaid Almaymuni, Mohammed A. Saleh, Sulaiman M. Ibrahim
article en

Abstract

This paper introduces a hardware-implemented pseudo-random number generator (PRNG) driven by a constructed Novel 4D Hyperchaotic System with Hidden Attractors (N4DHSHA). The dynamical properties of the oscillator are rigorously investigated through Lyapunov exponent spectra, bifurcation diagrams, basins of attraction, and the 0–1 test for chaos, revealing a Maximal Lyapunov Exponent (MLE) of 4.4662 alongside robust multistability. Furthermore, the model demonstrates linear topological controllability via DC offset boosting and amplitude scaling. To resolve the challenge of digitizing delicate equilibrium-free attractors, we propose a dual Artificial Neural Network (ANN) core architecture consisting of a Predictor layer activated by a Log-Sigmoid function and a Refiner layer activated by a Hyperbolic Tangent Sigmoid function. The proposed generator is implemented on a Xilinx Virtex-6 FPGA utilizing the 32-bit IEEE-754 floating-point standard. By harvesting 18-bit Least Significant Bit slices per clock cycle, the system achieves a real-time throughput of 139.714 Mbps at a 139.714 MHz operating frequency. Post-synthesis evaluations indicate highly optimized hardware footprint metrics, consuming 63.69% of available slice registers and 3.13% of DSP48E1 slices. The statistical verification shows that the generated bitstreams pass all 16 sub-tests of the NIST SP 800 − 22 test suite with P-values exceeding 0.01, proving that the dual-core neural architecture successfully preserves hyperchaotic complexity to deliver an entropy source for secure communications and image encryption.

Scientific Reports
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (IN), Qassim University (SA), Kırklareli University (TR), A'Sharqiyah University (OM), University Center of Barika (DZ), Sultan Zainal Abidin University (MY), Afyon Kocatepe University (TR), Saveetha University (IN)
Qassim University
Chaos-based Image/Signal Encryption
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon