<abstract><p>The fast development of the internet of things has been associated with the complex worldwide problem of protecting interconnected devices and networks. The protection of cyber security is becoming increasingly complicated due to the enormous growth in computer connectivity and the number of new applications related to computers. Consequently, emerging intrusion detection systems could execute a potential cyber security function to identify attacks and variations in computer networks. An efficient data-driven intrusion detection system can be generated utilizing artificial intelligence, especially machine learning methods. Deep learning methods offer advanced methodologies for identifying abnormalities in network traffic efficiently. Therefore, this article introduced a weighted salp swarm algorithm with deep learning-powered cyber-threat detection and classification (WSSADL-CTDC) technique for robust network security, with the aim of detecting the presence of cyber threats, keeping networks secure using metaheuristics with deep learning models, and implementing a min-max normalization approach to scale the data into a uniform format to accomplish this. In addition, the WSSADL-CTDC technique applied the shuffled frog leap algorithm (SFLA) to elect an optimum subset of features and applied a hybrid convolutional autoencoder (CAE) model for cyber threat detection and classification. A WSSA-based hyperparameter tuning method can be employed to enhance the detection performance of the CAE model. The simulation results of the WSSADL-CTDC system were examined in the benchmark dataset. The extensive analysis of the accuracy of the results found that the WSSADL-CTDC technique exhibited a better value of 99.13% than comparable methods on different measures.</p></abstract>