Comparison of Machine Learning Algorithms in Luflow Dataset
Abhishek A Nair, Neethumol Tomy, Amujuru Venkata Mahesh · 2023
Network traffic is a major target of cyberattacks, and an alert is sent to the system when potential threats are detected. A machine learning based IDS evaluation is suggested to create a dataset following the training dataset to eliminate behaviors from the dataset. The suggested approach can more accurately assess the long-term performance of ML-based IDS since the test dataset represents attack trends and modifications in network architecture over time. This study utilises the Luflow dataset to investigate the use of machine learning methods for the detection of network intrusions. A few machine-learning methods were used in the research to categorize network data into good and bad exploits. To increase the model's precision, the dataset was pre-processed, and features were chosen. The hyperparameters that were produced by enhancing the model's training and testing precision metrics were used to assess the model's performance. This work establishes a foundation for future research in the area and shows how machine learning algorithms are successful at detecting intrusions.