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

Abstract

The advancement of sixth-generation (6G) mobile networks introduces significant security challenges, particularly side-channel attacks (SCAs) that exploit physical leakages such as power consumption and electromagnetic emissions to extract sensitive information. Traditional cryptographic methods are inadequate against these attacks, necessitating intelligent and adaptive security solutions.This study presents a review of secure Artificial Intelligence (AI) techniques for 6G mobile devices, focusing on Deep Kronecker Neural Networks (DKNN) optimized with Hybrid Cat Hunting Optimization (HCHO). DKNN reduces computational complexity through Kronecker factorization while maintaining high learning capability, making it suitable for resource-constrained environments. HCHO enhances model performance by optimizing parameters and improving convergence speed.Recent research indicates that deep learning-based approaches significantly improve side-channel attack detection accuracy compared to conventional methods. Hybrid architectures further enhance robustness by capturing complex spatial and temporal features.

The review highlights key advancements, challenges, and future directions in secure AI for 6G systems. It concludes that integrating DKNN with advanced optimization techniques provides an efficient, scalable, and robust framework for mitigating side-channel attacks in next-generation mobile networks