A Neural Network Based Anomaly Intrusion Detection System

“…The model used ANN for classification of anomalous network traffic from normal traffic. Authors had calculated detection rate and false positive rate for three scenarios-(1) Detection only scenario, (2) Detection and classification, (3) Detection and detailed classification [14]. In their experiment, the system performance degraded as the system had been subjected to detect more specific attack, or attack types or sub-types.…”

Section: Available Offline Machine Learning Based Intrusion Detectionmentioning

confidence: 98%

“…Al-Janabi and Saeed [14] proposed a four stage/module model for anomaly-based NIDS. The four stages are (1) Monitoring Module, (2) Detection Module, (3) Classification Module, and (4) Alert Module.…”

Section: Available Offline Machine Learning Based Intrusion Detectionmentioning

confidence: 99%

Analysis of Machine Learning Techniques Based Intrusion Detection Systems

Sharma

Kalita

Borah

2015

Proceedings of 3rd International Conference on Advanced Computing, Networking and Informatics

View full text Add to dashboard Cite

Attacks on Computer Networks are one of the major threats on using Internet these days. Intrusion Detection Systems (IDS) are one of the security tools available to detect possible intrusions in a Network or in a Host. Research showed that application of machine learning techniques in intrusion detection could achieve high detection rate as well as low false positive rate. This paper discusses some commonly used machine learning techniques in Intrusion Detection System and also reviews some of the existing machine learning IDS proposed by authors at different times.

show abstract

“…In their system, to increase attacks coverage, CIDS integrates knowledge-based and behavior-based approaches and monitors each node to identify local events. In 2011, Al-Janabi and Saeed [11] developed an anomaly-based Intrusion Detection System which can quickly detect and classify various attacks. They have used Back Propagation Artificial Neural Network to learn system's behavior.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Cloud Network Intrusion Detection System

Ghosh

Mandal

Kumar

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Cloud Computing is an Internet based Computing where virtual shared servers provide software, infrastructure, platform and other resources to the customer on pay-as-you-use basis. With the enormous use of Cloud, the probability of occurring intrusion also increases. Intrusion Detection System (IDS) is a stronger strategy to provide security. In this paper, we have proposed an efficient, fast and secure IDS with the collaboration of multi-threaded Network Intrusion Detection System (NIDS) and Host Intrusion Detection System (HIDS). In the existing system, Cloud-IDS capture packets from Network, analyze them and send reports to the Cloud Administrator on the basis of analysis. Analysis of packets is done using K-Nearest Neighbor and Neural Network (KNN-NN) hybrid classifier. For training and testing purpose here we have used NSL-KDD dataset. After getting the report from the Cloud-IDS, Cloud Service Provider (CSP) will generate an alert for the user as well as maintain a loglist for storing the malicious IP addresses. Our proposed model handles large flow of data packets, analyze them and generate reports efficiently integrating anomaly and misuse detection.

show abstract

A Neural Network Based Anomaly Intrusion Detection System

Cited by 46 publications

References 4 publications

Intrusion Detection System: A Review

Intrusion Detection System: A Review

Analysis of Machine Learning Techniques Based Intrusion Detection Systems

An Efficient Cloud Network Intrusion Detection System

Contact Info

Product

Resources

About