Optimizing CNN for IoT Anomaly Detection in 6G using Ant Lion Optimizer and Slime Mould Algorithm

The fast spread of the Internet of Things (IoT) and the approaching deployment of 6G networks have presented hitherto unheard-of possibilities and problems in network security. IoT devices have become main targets for advanced attacks because they have personal and private information of the users. In this context, using the Ant Lion Optimizer for feature selection and the slime mould algorithm for hyperparameter tuning, we offer an optimal CNN model for anomaly detection in IoT devices within 6G networks. The proposed model identifies different IoT-related threats with an accuracy of 83%. Comparative comparison with conventional machine learning and deep learning models shows that our method greatly lowers average loss, therefore guaranteeing strong performance in settings with limited resources.