Abstract:
Daily interactions and networks require network security. As attackers develop new attacks and networks grow, intrusion detection systems are essential. Deep learning algorithms and artificial neural networks that can generate features automatically without human intervention have replaced machine learning algorithms in many studies to develop an effective IDS.
We created a hybrid intrusion detection system model using the Convolutional Neural Network’s spatial features and the Long Short-Term Memory Network’s temporal features. To improve performance, we added batch normalization and dropout layers.
Three datasets—CIC-IDS 2017, UNSW-NB15, and WSN-DS—trained the model for binary and multiclass classification. The confusion matrix evaluates the system’s accuracy, precision, detection rate, F1-score, and FAR. Experimental results showed the model’s high detection rate, accuracy, and low FAR.
Keywords: Feature Extraction, Convolutional Neural Networks, Intrusion Detection, Deep Learning, Training Data, Machine Learning Algorithms, Wireless Sensor Networks, Computer Network Security, Convolutional Neural Nets, Data Handling, Deep Learning (Artificial Intelligence), Feature Extraction, Matrix Algebra, Pattern Classification, Recurrent Neural Nets
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
