Network Intrusion Detection through Stacking Dilated Convolutional Autoencoders

Abstract

Network intrusion detection is one of the most important parts for cyber security to protect computer systems against malicious attacks. With the emergence of numerous sophisticated and new attacks, however, network intrusion detection techniques are facing several significant challenges. The overall objective of this study is to learn useful feature representations automatically and efficiently from large amounts of unlabeled raw network traffic data by using deep learning approaches. We propose a novel network intrusion model by stacking dilated convolutional autoencoders and evaluate our method on two new intrusion detection datasets. Several experiments were carried out to check the effectiveness of our approach. The comparative experimental results demonstrate that the proposed model can achieve considerably high performance which meets the demand of high accuracy and adaptability of network intrusion detection systems (NIDSs). It is quite potential and promising to apply our model in the large-scale and real-world network environments.

N-BaIoT—Network-Based Detection of IoT Botnet Attacks Using Deep Autoencoders

“…Such works within the greater domain of cybersecurity have been published more recently, yet they are dissimilar to our approach, unrelated to the IoT, and often not directly connected to botnets. For instance, [15], [16] and [18] applied shallow autoencoders for preliminary feature learning and dimensionality reduction, followed by Random Forest, Deep Belief Networks, and Softmax, respectively for classification and fine-tuning. Although autoencoders were extended for outlier detection in [17], they still required security analysts to actively label data for subsequent supervised learning.…”

Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey

“…Extracting payload features with unsupervised learning is also an effective detection method. Yu et al [45] utilized a convolutional autoencoder to extract payload features and conducted experiments on the CTU-UNB dataset. This dataset includes the raw packets of 8 attack types.…”

A Survey of Deep Learning Methods for Cyber Security

“…Yu et al [150] developed a network intrusion detection algorithm using dilated convolutional autoencoders (DCAEs) to identify normal and malicious traffic. Dilated convolutions are similar to regular convolutions, but there are gaps in between the applications of the kernel.…”