فهرست نشریات علمی دسترسی آزاد ایران

Intrusion Detection Systems (IDS) are critical for securing computer networks by identifying and analyzing unauthorized or abnormal activities, thereby preventing cyberattacks. Due to the increasing complexity and volume of network data, there is a growing demand for advanced and efficient data analysis methods. This study proposes a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks to enhance the accuracy and robustness of intrusion detection. Initially, CNNs are employed to extract spatial features from raw network traffic data. These features are then processed by a BiLSTM network to capture temporal dependencies and contextual relationships. To further improve classification performance, three machine learning classifiers-k-Nearest Neighbors (k-NN), Decision Tree, and Support Vector Machine (SVM) are trained on the extracted features, and their outputs are integrated using a weighted voting ensemble method. The proposed model is evaluated using the NSL-KDD dataset, achieving an accuracy of 99% in binary classification and 99.12\% in multi-class classification. The results demonstrate the effectiveness of the CNN–BiLSTM hybrid approach in accurately detecting both known and complex attack patterns in network traffic.