An Intrusion Detection Model Based on Deep Belief Networks

Gao, Ni; Gao, Ling; Gao, Quanli; Wang, Hai

doi:10.1109/cbd.2014.41

Cited by 226 publications

(100 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used real-world traffic traces and KDD Cup-99 [4] intrusion dataset in their implementation. In [14], Gao et al used RBM based DBN with a neural network as a classifier to implement an NIDS on KDD-Cup 99 dataset. In [17], Kang et al proposed an NIDS for the security of in-vehicular networks using DBN and improved detection accuracy compared to previous approaches.…”

Section: Intrusion Detection Using DLmentioning

confidence: 99%

A Deep Learning Based DDoS Detection System in Software-Defined Networking (SDN)

Niyaz¹,

Sun²,

Javaid³

2017

ICST Transactions on Security and Safety

201

125

View full text Add to dashboard Cite

Distributed Denial of Service (DDoS) is one of the most prevalent attacks that an organizational network infrastructure comes across nowadays. We propose a deep learning based multi-vector DDoS detection system in a software-defined network (SDN) environment. SDN provides flexibility to program network devices for different objectives and eliminates the need for third-party vendor-specific hardware. We implement our system as a network application on top of an SDN controller. We use deep learning for feature reduction of a large set of features derived from network traffic headers. We evaluate our system based on different performance metrics by applying it on traffic traces collected from different scenarios. We observe high accuracy with a low false-positive for attack detection in our proposed system.

show abstract

Section: Intrusion Detection Using DLmentioning

confidence: 99%

A Deep Learning Based DDoS Detection System in Software-Defined Networking (SDN)

Niyaz¹,

Sun²,

Javaid³

2017

ICST Transactions on Security and Safety

201

125

View full text Add to dashboard Cite

show abstract

“…There have been many approaches to intrusion detection using DL. Gao et al [120] used a DBN. The best performing algorithm was a DBN with four hidden layers (six layers total), beating an SVM and DBNs with fewer layers.…”

Section: Network Intrusion Detectionmentioning

confidence: 99%

A Survey of Deep Learning Methods for Cyber Security

et al. 2019

View full text Add to dashboard Cite

This survey paper describes a literature review of deep learning (DL) methods for cyber security applications. A short tutorial-style description of each DL method is provided, including deep autoencoders, restricted Boltzmann machines, recurrent neural networks, generative adversarial networks, and several others. Then we discuss how each of the DL methods is used for security applications. We cover a broad array of attack types including malware, spam, insider threats, network intrusions, false data injection, and malicious domain names used by botnets.

show abstract

“…With the advances in technology, the deep learning is paving its way to solve all the complex problems of modern era. These problems range from automatic image classification to intrusion detection [13], [14]. In this paper, the application of deep learning for automatic traffic control in VCPS is described.…”

Section: Deep Learning For Traffic Controlmentioning

confidence: 99%

SeDaTiVe: SDN-Enabled Deep Learning Architecture for Network Traffic Control in Vehicular Cyber-Physical Systems

et al. 2018

View full text Add to dashboard Cite

The rapid growth in the transportation sector has led to the emergence of smart vehicles which are equipped with information and communication technologies (ICT). These modern smart vehicles are connected to the Internet to have various services such as road condition information, infotainment, and energy management. This kind of scenario can be viewed as vehicular cyber-physical system (VCPS) where the vehicles are at physical layer and services are at cyber layer. However, network traffic management is the biggest issue in the modern VCPS scenario as the mismanagement of the network resources can degrade the quality of service (QoS) for the end users. To deal with this issue, we propose a software defined network (SDN)-enabled approach, named SeDaTiVe, which used deep learning architecture to control the incoming traffic in the network in VCPS environment. The advantage of using deep learning in network traffic control is that it learns the hidden patterns in the data packets and creates an optimal route based on the learned features. Moreover, a virtual controller based scheme for flow management using SDN in VCPS is designed for effective resource utilization for providing QoS. The simulation scenario comprising of 1000 vehicles seeking various services in the network is considered to generate the dataset using SUMO. The data obtained from the simulation study is evaluated using NS-2 which proves that the proposed scheme effectively handles the real-time incoming requests in VCPS. The results also depict the improvement in performance on various evaluation metrics like delay, throughput, packet delivery ratio, and network load by using the proposed scheme over the traditional SDN and TCP/IP protocol suite.Index Terms-Traffic control, deep learning, software-defined network, vehicular cyber-physical system. ! • A. Jindal is with the

show abstract

An Intrusion Detection Model Based on Deep Belief Networks

Cited by 226 publications

References 9 publications

A Deep Learning Based DDoS Detection System in Software-Defined Networking (SDN)

A Deep Learning Based DDoS Detection System in Software-Defined Networking (SDN)

A Survey of Deep Learning Methods for Cyber Security

SeDaTiVe: SDN-Enabled Deep Learning Architecture for Network Traffic Control in Vehicular Cyber-Physical Systems

Contact Info

Product

Resources

About