NETWORK-BASED INTRUSION DETECTION SYSTEM USING MACHINE LEARNING

Strong network security solutions are more important than ever in a time when cyber threats are ever morecomplex. Because cybercriminals are always coming up with new ways to attack, standard security measures areno longer enough. The goal of this project is to create and deploy an intrusion detection system (IDS) that canquickly identify and neutralize possible online threats Our intrusion detection system uses a hybrid strategy thatcombines anomaly-based detection, which uses machine learning to identify departures from typical networkbehaviour, with signature-based detection, which finds known attack patterns. Combining these two methodsimproves the system's accuracy and flexibility, allowing it to recognize both known threats and new intrusionsto develop and evaluate our IDS, we utilized the CIC-IDS-2017 dataset, a benchmark dataset for intrusiondetection research. The IDS was implemented using Python and key machine learning libraries such as Scikitlearn, TensorFlow, and Pandas. The system was trained and tested on a wide range of network traffic scenarios,ensuring its robustness in detecting various types of cyber threats We have added a Face Identification Featureto the IDS to further improve security. When someone tries to access vital network infrastructure, this functionauthenticates them using facial recognition based on deep learning. The system uses OpenCV and Face-Net toverify IDs in real time, preventing critical data from being accessed by unauthorized personnel. Becausebiometric authentication provides an additional layer of security, it is far more difficult for hackers to get aroundsecurity measures using social engineering or credential theft.