A Hybrid Intrusion Detection Model Combining SAE with Kernel Approximation in Internet of Things
| Autor: | Xuan Gong, Wei William Lee, Yukun Wu, Hui Wang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
kernel approximation Feature vector intrusion detection 02 engineering and technology Intrusion detection system lcsh:Chemical technology Biochemistry Article Analytical Chemistry symbols.namesake 0202 electrical engineering electronic engineering information engineering Gaussian function lcsh:TP1-1185 support vector machine Electrical and Electronic Engineering Instrumentation random Fourier feature NSL-KDD 020208 electrical & electronic engineering Autoencoder Atomic and Molecular Physics and Optics Support vector machine Feature Dimension Feature (computer vision) stacked auto-encoder symbols 020201 artificial intelligence & image processing Algorithm Curse of dimensionality |
| Zdroj: | Sensors Volume 20 Issue 19 Sensors, Vol 20, Iss 5710, p 5710 (2020) Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s20195710 |
| Popis: | Owing to the constraints of time and space complexity, network intrusion detection systems (NIDSs) based on support vector machines (SVMs) face the &ldquo curse of dimensionality&rdquo in a large-scale, high-dimensional feature space. This study proposes a joint training model that combines a stacked autoencoder (SAE) with an SVM and the kernel approximation technique. The training model uses the SAE to perform feature dimension reduction, uses random Fourier features to perform kernel approximation, and then random Fourier mapping is explicitly applied to the sub-sample to generate the random feature space, making it possible to apply a linear SVM to uniformly approximate to the Gaussian kernel SVM. Finally, the SAE performs joint training with the efficient linear SVM. We studied the effects of an SAE structure and a random Fourier feature on classification performance, and compared that performance with that of other training models, including some without kernel approximation. At the same time, we compare the accuracy of the proposed model with that of other models, which include basic machine learning models and the state-of-the-art models in other literatures. The experimental results demonstrate that the proposed model outperforms the previously proposed methods in terms of classification performance and also reduces the training time. Our model is feasible and works efficiently on large-scale datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |