Enhancing Network Security through DIPS
Authors:-J. Sathishkumar, K. Dhanush, K. Aneesh, B. Vigneshwaran
Abstract- Network Intrusion Detection Systems (NIDS) play a crucial role in protecting computer networks from unauthorized access and harmful activities. This paper investigates the use of Machine Learning (ML) techniques to improve the effectiveness of NIDS in detecting network intrusions. The approach involves gathering a comprehensive dataset of both legitimate and malicious network traffic, extracting important features, and labeling data for supervised learning. Various machine learning models, such as Decision Trees, XGBoost, and Artificial Neural Networks, are assessed for their ability to differentiate between normal and malicious network behavior. The models are rigorously tested and fine-tuned to ensure precise and dependable intrusion detection. Additionally, the system notifies the user through reporting. For real-time operation, the ML-powered NIDS continuously monitors network traffic using a Denial of Intrusion Detection and Prevention System (DIPS), offering the capability to adjust to evolving conditions and new threats.
