Skip to main content
main-content

Über dieses Buch

This book presents recent advances in intrusion detection systems (IDSs) using state-of-the-art deep learning methods. It also provides a systematic overview of classical machine learning and the latest developments in deep learning. In particular, it discusses deep learning applications in IDSs in different classes: generative, discriminative, and adversarial networks. Moreover, it compares various deep learning-based IDSs based on benchmarking datasets. The book also proposes two novel feature learning models: deep feature extraction and selection (D-FES) and fully unsupervised IDS. Further challenges and research directions are presented at the end of the book.

Offering a comprehensive overview of deep learning-based IDS, the book is a valuable reerence resource for undergraduate and graduate students, as well as researchers and practitioners interested in deep learning and intrusion detection. Further, the comparison of various deep-learning applications helps readers gain a basic understanding of machine learning, and inspires applications in IDS and other related areas in cybersecurity.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
This chapter discusses the importance of IDS in computer networks while wireless networks grow rapidly these days by providing a survey of a security breach in wireless networks. Many methods have been used to improve IDS performance, the most promising one is to deploy machine learning. Then, the usefulness of recent models of machine learning, called a deep learning, is highlighted to improve IDS performance, particularly as a Feature Learning (FL) approach. We also explain the motivation of surveying deep learning-based IDSs.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Chapter 2. Intrusion Detection Systems

Abstract
This chapter briefly introduces all the relevant definitions on Intrusion Detection System (IDS), followed by a classification of current IDSs, based on the detection module located and the approach adopted. We also explain and provide examples of one common IDS in research fields, which is machine-learning-based IDS. Then, we discuss an example of IDS using bio-inspired clustering method.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Chapter 3. Classical Machine Learning and Its Applications to IDS

Abstract
This chapter provides a brief preliminary study regarding classical machine learning which consists of six different models: supervised, unsupervised, semi-supervised, weakly supervised, reinforcement, and adversarial machine learning. Then, the 22 papers are surveyed, which use machine-learning techniques for their IDSs.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Chapter 4. Deep Learning

Abstract
This chapter defines a brief history and definition of deep learning. Due to a variety of models belonging to deep learning, we classify deep learning models into a tree which has three branches: generative, discriminative, and hybrid. In each model, we show some learning model examples in order to see the difference among three models.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Chapter 5. Deep Learning-Based IDSs

Abstract
This chapter reviews recent IDSs leveraging deep learning models as their methodology which were published during 2016 and 2017. The critical issues like problem domain, methodology, dataset, and experimental result of each publication will be discussed. These publications can be classified into three different categories according to deep learning classification in Chap. 4, namely, generative, discriminative, and hybrid. The generative model group consists of IDSs that use deep learning models for feature extraction only and use shallow methods for the classification task. The discriminative model group contains IDSs that use a single deep learning method for both feature extraction and classification task. The hybrid model group includes IDSs that use more than one deep learning method for generative and discriminative purposes. All IDSs are compared to overview the advancement of deep learning in IDS researches.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Chapter 6. Deep Feature Learning

Abstract
FL is a technique that models the behavior of data from a subset of attributes only. It also shows the correlation between detection performance and traffic model quality efficiently (Palmieri et al., Concurrency Comput Pract Exp 26(5):1113–1129, 2014). However, feature extraction and feature selection are different. Feature extraction algorithms derive new features from the original features to (i) reduce the cost of feature measurement, (ii) increase classifier efficiency, and (iii) improve classification accuracy, whereas feature selection algorithms select no more than m features from a total of M input features, where m is smaller than M. Thus, the newly generated features were merely selected from the original features without any transformation. However, their goal is to derive or select a characteristic feature vector with a lower dimensionality which is used for the classification task. One advantage of deep learning models is processing underlying data from the input which suits for FL tasks. Therefore, we discuss this critical role of deep learning in IDS as Deep Feature Extraction and Selection (D-FES) and deep learning for clustering.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Chapter 7. Summary and Further Challenges

Abstract
This last chapter concludes this monograph by providing a closing statement regarding the advantage of using deep learning models for IDS purposes and why those models can improve IDS performance. Afterward, the overview of challenges and future research directions in deep learning applications for IDS is suggested.
Kwangjo Kim, Muhamad Erza Aminanto, Harry Chandra Tanuwidjaja

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise