Identifying important features for intrusion detection using support vector machines and neural networks

By Andrew H. Sung, Srinivas Mukkamala. 2003 Symposium on Applications and the Internet, 2003. Proceedings., 2003

460 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/3f4706f89e6ca4fe27674b43f51c27f494a0eb15

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Networks and Communications

Citations in the corpus

AdaBoost-Based Algorithm for Network Intrusion Detection (2008, background): “…for intrusion detection using hierarchical NNs. Han and Cho [38] use evolutionary NNs to detect intrusions. b) SVM-based approaches: Mukkamala et al. [39], [40] use SVMs to distinguish between normal network behaviors and intrusions and further identify important features for intrusion detection.”
RETRACTED ARTICLE: Application of extreme learning machine for estimation of wind speed distribution (2016, methodology): “SVMs have better performance compared to other traditional techniques such as NN and other conventional statistical models (Collobert and Bengio 2000; Huang et al. 2002; Mukkamala et al. 2002; Sung and Mukkamala 2003; Vapnik et al. 1997; Vapnik 2000).”
An Implementation of Intrusion Detection System Using Genetic Algorithm (2012, background): “Every attack on a network can comfortably be placed into one of these groupings [21].”
A new hybrid support vector machine–wavelet transform approach for estimation of horizontal global solar radiation (2015, methodology): “It has been proved that its applications show superior performance compared to prior developed methodologies such as neural network and other conventional statistical models [50–55].”
An overview of anomaly detection techniques: Existing solutions and latest technological trends (2007, methodology): “adopted by Sung and Mukkamala [66] that use a SVM technique to realize an intrusion detection system for class-specific detection is flawed because they totally ignore the relationships and dependencies between the features.”
A hybrid machine learning approach to network anomaly detection (2007, methodology): “Recently, it has also been applied to inform security for intrusion detection [17,20,40].”
Network Anomaly Detection: Methods, Systems and Tools (2014, methodology): “Several other methods for feature selection are [39], [63]–[65].”
Long Short Term Memory Recurrent Neural Network Classifier for Intrusion Detection (2016, methodology): “Andrew H. Sung et al. took an IDS performance test with Support Vector Machine (SVM) and Artificial Neural Networks (ANN) [4].”
Intrusion detection model using fusion of chi-square feature selection and multi class SVM (2016, background): “Sung and Mukkamala (2003) eliminated one feature at every time instance to conduct experiments on SVM integrated with neural network.”
Survey of intrusion detection systems: techniques, datasets and challenges (2019, background): “Each attack type can be classified into one of the following four classes (Sung & Mukkamala, 2003): Denial-of-Service (DoS) attacks have the objective of blocking or restricting services delivered by the network, computer to the users.”
Feature deduction and ensemble design of intrusion detection systems (2005, methodology): “Feature selection improves classification by searching for the subset of features, which best classifies the training data (Sung and Mukkamala, 2003).”