NEURO-BIOMETRIC SECURITY FOR 6G EDGE NETWORKS: GENETIC AI–INSPIRED ACCURACY AND COMPUTATIONAL EFFICIENCY ANALYSIS

Abstract

Scientific culture permeates almost every aspect of the design and development of next-generation communication systems. The principles of trustworthy innovation, reproducibility, ethical Genetic-AI, and sustainability define the current scientific culture. EEG-based neuro-biometric authentication systems have great potential for securing 6G edge networks against several types of attacks. However, the authentication system must strike a balance between security, efficiency, and latency requirements.

A scientific culture–inspired framework based on EEG signal classification and neuro-biometric authentication is proposed in this paper. The framework includes preprocessing, feature extraction using the PCA-integrated BTO++ model, an optimization algorithm inspired by biological systems, and a homomorphic encryption scheme that enables secure inference of the authentication model. Experimental results demonstrate the high accuracy of the PCA-integrated BTO++ model for neuro-biometric authentication while maintaining a low computational cost during the encrypted inference step. The results also show that classical machine learning models can satisfy the requirements for 6G networks without depending on quantum computing infrastructures. The proposed system presents trustworthy solutions for cyber-security in human-centric networks and fosters scientific culture in the next generation of secure 5G and 6G communication systems.