PNrule: A New Framework for Learning Classifier Models in Data Mining (A Case-Study in Network Intrusion Detection)

Agarwal, R.; Joshi, Manjunath V.

doi:10.1137/1.9781611972719.29

Cited by 103 publications

(54 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first three places were occupied by entries that used variants of decision trees and showed only marginal differences in performance [13,14,15]. In ninth place in the challenge, was the 1-nearest neighbour classifier.…”

Section: Related Workmentioning

confidence: 99%

Applying long short-term memory recurrent neural networks to intrusion detection

Staudemeyer¹

2015

SACJ

179

View full text Add to dashboard Cite

We claim that modelling network traffic as a time series with a supervised learning approach, using known genuine and malicious behaviour, improves intrusion detection. To substantiate this, we trained long short-term memory (LSTM) recurrent neural networks with the training data provided by the DARPA / KDD Cup ’99 challenge. To identify suitable LSTM-RNN network parameters and structure we experimented with various network topologies. We found networks with four memory blocks containing two cells each offer a good compromise between computational cost and detection performance. We applied forget gates and shortcut connections respectively. A learning rate of 0.1 and up to 1,000 epochs showed good results. We tested the performance on all features and on extracted minimal feature sets respectively. We evaluated different feature sets for the detection of all attacks within one network and also to train networks specialised on individual attack classes. Our results show that the LSTM classifier provides superior performance in comparison to results previously published results of strong static classifiers. With 93.82% accuracy and 22.13 cost, LSTM outperforms the winning entries of the KDD Cup ’99 challenge by far. This is due to the fact that LSTM learns to look back in time and correlate consecutive connection records. For the first time ever, we have demonstrated the usefulness of LSTM networks to intrusion detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Applying long short-term memory recurrent neural networks to intrusion detection

Staudemeyer¹

2015

SACJ

179

View full text Add to dashboard Cite

show abstract

“…For the evaluation results, we made use of about 10% of the full huge data set which amounted to about 27000 data points. The performance evaluation was made for both testing 0 50 100 KDD 99 Winner [36] PNrule [37] Class SVM [38] Layered conditional random fields [39] Columbia Model [40] Decision tree [41] BPNN [42] Our Technique U2R Attacks 0 50 100 KDD 99 Winner [36] PNrule [37] Class SVM [38] Layered conditional random fields [39] Columbia Model [40] Decision tree [41] BPNN [42] Our Technique…”

Section: U2r Attacksmentioning

confidence: 99%

Fortification of Hybrid Intrusion Detection System Using Variants of Neural Networks and Support Vector Machines

Azad¹,

Raghuveer²

2013

IJNSA

View full text Add to dashboard Cite

Intrusion Detection Systems (IDS) form a key part of system defence, where it identifies abnormal activities happening in a computer system. In recent years different soft computing based techniques have been proposed for the development of IDS. On the other hand, intrusion detection is not yet a perfect technology. This has provided an opportunity for data mining to make quite a lot of important contributions in the field of intrusion detection. In this paper we have proposed a new hybrid technique by utilizing data mining techniques such as fuzzy C means clustering, Fuzzy neural network / Neurofuzzy and radial basis function(RBF) SVM for fortification of the intrusion detection system. The proposed technique has five major steps in which, first step is to perform the relevance analysis, and then input data is clustered using Fuzzy C-means clustering. After that, neuro-fuzzy is trained, such that each of the data point is trained with the corresponding neuro-fuzzy classifier

show abstract

“…In general, intrusion detection method is divided into signature-based intrusion detection or anomaly-based intrusion detection system (ads). SD is a known process comparison signature pattern attack or threat to capture events to identify possible invasion [1][2]. Found in the process of advertising from a known behavior, behavior and construct summary on behalf of the normal or expected from monitoring routine activities, network connection, the host or the user for a period of time.…”

Section: Introductionmentioning

confidence: 99%

Research on Principle Techniques for Network Intrusion Detection based on Data Mining and Analysis Approach

Jiang¹,

Chen²

2015

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Abstract. The security of software applications, from web-based applications to mobile services, is always at risk because of the open society of internet. With the increase in the number of network throughput and security threats, intrusion detection system has attracted much attention in recent years. In this paper, we undertake the research on the principle techniques for network intrusion detection based on data mining and analysis approach. We adopt the prior knowledge on Bayesian network which is a directed acyclic graph, each node represents a random variable and an edge said direct probabilistic dependencies between two connected nodes. Then, we use the traditional risk assessment model to measure the possibility of being hearted. The numeric analysis and experimental illustration indicates the effectiveness of our method compared with other popular adopted state-of-the-art methodologies. In the future, we plan to introduce the graph and complex network theory into our prototype system to enhance the performance.

show abstract

PNrule: A New Framework for Learning Classifier Models in Data Mining (A Case-Study in Network Intrusion Detection)

Cited by 103 publications

References 8 publications

Applying long short-term memory recurrent neural networks to intrusion detection

Applying long short-term memory recurrent neural networks to intrusion detection

Fortification of Hybrid Intrusion Detection System Using Variants of Neural Networks and Support Vector Machines

Research on Principle Techniques for Network Intrusion Detection based on Data Mining and Analysis Approach

Contact Info

Product

Resources

About