With the development of the Internet, cyber-attacks are changing rapidly and the cyber security situation is not optimistic. This survey report describes key literature surveys on machine learning (ML) and deep learning (DL) methods for network analysis of intrusion detection and provides a brief tutorial description of each ML/DL method. Papers representing each method were indexed, read, and summarized based on their temporal or thermal correlations. Because data are so important in ML/DL methods, they described some of the commonly used network datasets used in ML/DL, discussed the challenges of using ML/DL for cybersecurity and provided suggestions for research directions.

This paper presents a literature review of machine learning (ML) and deep learning (DL) methods for cybersecurity applications. ML/DL methods and some applications of each method in network intrusion detection are described. It focuses on ML and DL technologies for network security, ML/DL methods and their descriptions. Our research aims on standards-compliant publications that use “machine learning”, “deep learning” and cyber as keywords to search on Google Scholar. In particular, the new hot papers are used because they describe the popular techniques.

The purpose of this paper is for those who want to study network intrusion detection in ML/DL.Thus, great emphasis is placed on a thorough description of the ML/DL methods, and references to seminal works for each ML and DL method are provided. Examples are provided concerning how the techniques were used in cyber security.

The algorithms used for detection of cybersecurity threats is as follows:

 1. Convolutional Neural Network (CNN) 

2. Support Vector Machine (SVM)

 3. K-Nearest Neighbor (KNN)

 4. Decision Tree

 5. Deep Belief Network (DBN)

 6. Recurrent Neural Network (RNN)

COMPARISIONS OF RESULTS OF VARIOUS TECHNIQUES

Important points:

This survey report describes key literature surveys on machine learning (ML) and deep learning (DL) methods for network analysis of intrusion detection and provides a brief tutorial description of each ML/DL method

This paper presents a literature review of machine learning (ML) and deep learning (DL) methods for cybersecurity applications. ML/DL methods and some applications of each method in network intrusion detection are described

It focuses on ML and DL technologies for network security, ML/DL methods and their descriptions. Our research aims on standards-compliant publications that use “machine learning”, “deep learning” and cyber as keywords to search on Google Scholar

The purpose of this paper is for those who want to study network intrusion detection in ML/DL.