Anomaly Detection in Software-Defined Networks Using Cross-Validation

The topic of the work was the detection of anomalies in software-defined networks (SDN) with the appropriate selection and use of artificial intelligence algorithms and their parameters. As part of the work, the research was carried out on six sets using the cross-validation method based on the RandomForest, xgboost algorithms and neural networks. The results of detecting attacks on the tested data oscillated on the average level of accuracy from 88.49% to 99.28%. This is a satisfactory result considering the most accurate test results. An innovation in the approach to the problem is that the algorithm works relatively efficiently regardless of the input set, as opposed to the current solutions, where the algorithm is adapted to a dedicated input set.