Recent Advances in Secure AI for 6G Mobile Devices: Deep Kronecker Neural Network Optimized with Hybrid Cat Hunting Optimization to Combat Side-Channel Attacks: A Systematic Review

Abstract

The rapid evolution of sixth-generation (6G) communication systems introduces unprecedented challenges in securing mobile devices against advanced cyber threats, particularly side-channel attacks (SCAs). These attacks exploit indirect information such as power consumption, timing variations, and electromagnetic emissions to compromise cryptographic systems. Traditional security mechanisms are insufficient to address these sophisticated threats, necessitating the integration of artificial intelligence (AI)-based defense mechanisms. This paper presents a systematic review of recent advances in secure AI for 6G mobile devices, focusing on Deep Kronecker Neural Networks (DKNN) optimized with Hybrid Cat Hunting Optimization (HCHO) for mitigating side-channel attacks. The study reviews literature from recent years, highlighting the role of deep learning, reinforcement learning, and hybrid optimization techniques in detecting and preventing SCAs. The findings indicate that AI-driven models achieve high detection accuracy, with some approaches reaching approximately 95% effectiveness in identifying side-channel exploits . Furthermore, hybrid optimization techniques enhance model performance by improving convergence speed and reducing computational overhead. The paper also discusses emerging trends, including AI-driven cryptography, adversarial defense mechanisms, and quantum-enhanced security. Finally, key challenges and future research directions are identified for developing robust, scalable, and energy-efficient security solutions in 6G environments.