<p>Detecting network intrusions is crucial for maintaining network security. Early detection of attacks reduces potential damage, protects sensitive data and critical systems, enables rapid response, prevents financial losses such as data breaches, and recovers. This involves analyzing network traffic data to identify potential cyber threats. However, the dimensionality problem poses a challenge due to the large number of dimensions in the data. To overcome this challenge, feature selection is a key step in building effective intrusion detection systems. It involves removing irrelevant and redundant features, which helps reduce the dimensionality of the feature space and improve the accuracy of the classification model. Metaheuristic algorithms are nature-inspired optimization techniques that are well suited for feature selection and network intrusion detection. They are effective in exploring large search spaces and have been widely used for this purpose. In this paper, a hybrid method called ISCA-GRO, which is based on the modified Sine–Cosine algorithm and the Golden Ratio based Optimization algorithm, is proposed. Here, first, a pre-processed dataset is used, then an improved version of the SCA algorithm is proposed for feature selection, which introduces a control parameter to balance exploration and exploitation, and then the GRO algorithm is used to detect cyber attacks. The performance of the proposed algorithm is evaluated on the NSL-KDD and UNSW-NB15 datasets and compared with other algorithms. The evaluation results show that the proposed method outperforms other meta-heuristic algorithms in terms of the number of selected features and classification accuracy, and can also be used as an effective method for feature selection and intrusion detection.</p>