Currently, it is very important to maintain high -level security to ensure safe and trusted communication of information between various organizations. There has been much research conducted on intrusion detection in the past, especially anomaly based intrusion detection. In this paper, we use MLP for intrusion classification by using the CIC-IDS2018 dataset. Feature extraction is part of SelectKbest. These are used to test the attacks on binary and multiclass. The results found that the MLP with SelectKbest feature gives the performance with high performance. This method is capable of minimizing the number of features and maximizing the detection rates.