Character-Level Intrusion Detection Based On Convolutional Neural Networks

Abstract

Deep learning models are increasingly applied in the intrusion detection system (IDS) and propel its development nowadays. In this paper, a new character-level IDS is proposed based on convolutional neural networks and obtains better performance. Different from other models which are in the feature level, this model is in the character level, which views network traffic records as sequences of characters. Each character of a record is encoded into a vector based on an alphabet. The vectors of the characters in the record are aggregated into a matrix as the input of the convolutional neural networks with an improved structure. This model simplifies the preprocessing without considering the priori knowledge about the data. Experiments on the dataset NSL-KDD show that the binary classification and the multi-classification of our model have good performance. Compared with other machine learning algorithms in term of accuracy, our model outperforms those algorithms. The comparison with the model using convolutional neural networks with the preprocessing in the feature level reveals that our model performs much better with high accuracy, high detection rate and low false alarm rate.