Intrusion detection systems play an important role in preventing security threats and protecting networks from attacks. However, with the emergence of unknown attacks and imbalanced samples, traditional machine learning methods suffer from lower detection rates and higher false positive rates. We propose a novel intrusion detection model that combines an improved conditional variational AutoEncoder (ICVAE) with a deep neural network (DNN), namely ICVAE-DNN. ICVAE is used to learn and explore potential sparse representations between network data features and classes. The trained ICVAE decoder generates new attack samples according to the specified intrusion categories to balance the training data and increase the diversity of training samples, thereby improving the detection rate of the imbalanced attacks. The trained ICVAE encoder is not only used to automatically reduce data dimension, but also to initialize the weight of DNN hidden layers, so that DNN can easily achieve global optimization through back propagation and fine tuning. The NSL-KDD and UNSW-NB15 datasets are used to evaluate the performance of the ICVAE-DNN. The ICVAE-DNN is superior to the three well-known oversampling methods in data augmentation. Moreover, the ICVAE-DNN outperforms six well-known models in detection performance, and is more effective in detecting minority attacks and unknown attacks. In addition, the ICVAE-DNN also shows better overall accuracy, detection rate and false positive rate than the nine state-of-the-art intrusion detection methods.

To explore the advantages of adversarial learning and deep learning, we propose a novel network intrusion detection model called SAVAER-DNN, which can not only detect known and unknown attacks but also improve the detection rate of low-frequent attacks. SAVAER is a supervised variational auto-encoder with regularization, which uses WGAN-GP instead of the vanilla GAN to learn the latent distribution of the original data. SAVAER's decoder is used to synthesize samples of low-frequent and unknown attacks, thereby increasing the diversity of training samples and balancing the training data set. SAVAER's encoder is used to initialize the weights of the hidden layers of the DNN and explore high-level feature representations of the original samples. The benchmark NSL-KDD (KDDTest+), NSL-KDD (KDDTest-21) and UNSW-NB15 datasets are used to evaluate the performance of the proposed model. The experimental results show that the proposed SAVAER-DNN is more suitable for data augmentation than the other three well-known data oversampling methods. Moreover, the proposed SAVAER-DNN outperforms eight well-known classification models in detection performance and is more effective in detecting low-frequent and unknown attacks. Furthermore, compared with other state-of-the-art intrusion detection models reported in the IDS literature, the proposed SAVAER-DNN offers better performance in terms of overall accuracy, detection rate, F1 score, and false positive rate.

In recent years, machine learning-based intrusion detection systems (IDSs) have proven to be effective; especially, deep neural networks improve the detection rates of intrusion detection models. However, as models become more and more complex, people can hardly get the explanations behind their decisions. At the same time, most of the works about model interpretation focuses on other fields like computer vision, natural language processing, and biology. This leads to the fact that in practical use, cybersecurity experts can hardly optimize their decisions according to the judgments of the model. To solve these issues, a framework is proposed in this paper to give an explanation for IDSs. This framework uses SHapley Additive exPlanations (SHAP), and combines local and global explanations to improve the interpretation of IDSs. The local explanations give the reasons why the model makes certain decisions on the specific input. The global explanations give the important features extracted from IDSs, present the relationships between the feature values and different types of attacks. At the same time, the interpretations between two different classifiers, one-vs-all classifier and multiclass classifier, are compared. NSL-KDD dataset is used to test the feasibility of the framework. The framework proposed in this paper leads to improve the transparency of any IDS, and helps the cybersecurity staff have a better understanding of IDSs' judgments. Furthermore, the different interpretations between different kinds of classifiers can also help security experts better design the structures of the IDSs. More importantly, this work is unique in the intrusion detection field, presenting the first use of the SHAP method to give explanations for IDSs.