In this paper, anomaly detection using neural network is introduced. This paper aims to experiment with user behavior as parameters in anomaly intrusion detection using a backpropagation neural network. Here the authors wanted to see if a neural network is able to classify normal traffic correctly, and detect known and unknown attacks without using a huge amount of training data. For the training and testing of the neural network, they used the DARPA intrusion detection evaluation data sets. In their final experiment, they have got a classification rate of 88% on known and unknown attacks.