Multilayer Perceptron and Auto-Encoder based Intrusion Detection System
G. Sahitya, C. Kaushik, Karthik K, Anemesh Chandra, Janaki Ram C · International Journal of Engineering Trends and Technology · 2024
In recent times, with the rapid growth of the internet, every day a lot of data is being generated. Along with this growth, there are advancements in cybersecurity attacks and the technologies through which security attacks are taking place; as a result, there is an increase in security and privacy concerns for users. An Intrusion Detection System can be developed to address this issue. The Intrusion Detection System can be made by evaluating several advanced computational deep learning and machine learning models for intrusion detection using datasets containing features extracted from network traffic; in this paper, using Deep Learning (DL) Techniques such as Multi-layer Perceptron (MLP) and Auto encoders (AE). These classifiers are being trained and evaluated on the dataset, and their performance metrics, including accuracy and classification reports, are being computed by using only the features which are necessary and useful. The Intrusion Detection Model, through these classifiers, improves the accuracy of intrusion detection.