Cyber Attack Detection

Cyber attack detection research aims to develop robust and adaptable systems capable of identifying diverse and evolving threats across various domains, including smart grids, IoV networks, and industrial control systems. Current research heavily utilizes machine learning, focusing on models like autoencoders (including variations such as adversarial and twin autoencoders), graph neural networks, and deep learning approaches incorporating techniques like federated learning, transfer learning, and self-supervised learning to address data scarcity and heterogeneity. These advancements are crucial for enhancing the security and reliability of critical infrastructure and digital systems, improving the accuracy and efficiency of threat detection while mitigating privacy concerns.