Intrusion Detection in KDD99 Dataset using SVM-PSO and Feature Reduction with Information Gain

Saxena, Harshit; Richariya, Vineet

doi:10.5120/17188-7369

Cited by 56 publications

(25 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…PSO performs feature optimization to obtain an optimized feature, after which SVM performs the classification task. A similar approach was introduced by Saxena and Richariya [26], although the concept of weighted feature selection was introduced by Schaffernicht and Gross [27]. Exploiting SVM-based algorithms as a feature selection method was introduced by Guyon et al [28].…”

Section: Related Workmentioning

confidence: 99%

Deep Abstraction and Weighted Feature Selection for Wi-Fi Impersonation Detection

Aminanto

Choi

Tanuwidjaja

et al. 2018

IEEE Trans.Inform.Forensic Secur.

183

View full text Add to dashboard Cite

The recent advances in mobile technologies have resulted in IoT-enabled devices becoming more pervasive and integrated into our daily lives. The security challenges that need to be overcome mainly stem from the open nature of a wireless medium such as a Wi-Fi network. An impersonation attack is an attack in which an adversary is disguised as a legitimate party in a system or communications protocol. The connected devices are pervasive, generating high-dimensional data on a large scale, which complicates simultaneous detections. Feature learning, however, can circumvent the potential problems that could be caused by the large-volume nature of network data. This study thus proposes a novel Deep-Feature Extraction and Selection (D-FES), which combines stacked feature extraction and weighted feature selection. The stacked autoencoding is capable of providing representations that are more meaningful by reconstructing the relevant information from its raw inputs. We then combine this with modified weighted feature selection inspired by an existing shallow-structured machine learner. We finally demonstrate the ability of the condensed set of features to reduce the bias of a machine learner model as well as the computational complexity. Our experimental results on a well-referenced Wi-Fi network benchmark dataset, namely, the Aegean Wi-Fi Intrusion Dataset (AWID), prove the usefulness and the utility of the proposed D-FES by achieving a detection accuracy of 99.918% and a false alarm rate of 0.012%, which is the most accurate detection of impersonation attacks reported in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Abstraction and Weighted Feature Selection for Wi-Fi Impersonation Detection

Aminanto

Choi

Tanuwidjaja

et al. 2018

IEEE Trans.Inform.Forensic Secur.

183

View full text Add to dashboard Cite

show abstract

“…As the KDD Cup 1999 dataset [25] has been widely used to evaluate various intrusion detection approaches, we perform a five-class flow classification using a subset of it after downsampling in this paper. The distribution of both training and testing data marked by their attack type is summarized in Table III. Algorithm 2 Improved Random forest Input:…”

Section: A Dataset and Evaluation Metricsmentioning

confidence: 99%

AI-Based Two-Stage Intrusion Detection for Software Defined IoT Networks

Zhao

et al. 2019

IEEE Internet Things J.

183

View full text Add to dashboard Cite

Software Defined Internet of Things (SD-IoT) Networks profits from centralized management and interactive resource sharing which enhances the efficiency and scalability of IoT applications. But with the rapid growth in services and applications, it is vulnerable to possible attacks and faces severe security challenges. Intrusion detection has been widely used to ensure network security, but classical detection means are usually signature-based or explicit-behavior-based and fail to detect unknown attacks intelligently, which are hard to satisfy the requirements of SD-IoT Networks. In this paper, we propose an AI-based two-stage intrusion detection empowered by software defined technology. It flexibly captures network flows with a globle view and detects attacks intelligently through applying AI algorithms. We firstly leverage Bat algorithm with swarm division and Differential Mutation to select typical features. Then, we exploit Random forest through adaptively altering the weights of samples using weighted voting mechanism to classify flows. Evaluation results prove that the modified intelligent algorithms select more important features and achieve superior performance in flow classification. It is also verified that intelligent intrusion detection shows better accuracy with lower overhead comparied with existing solutions.

show abstract

“…Saxena et al [8] considered the information gain ratio as a main aspect for feature selection criterion and developed an SVM integrated IDS with particle swarm optimization (PSO) [17] as an optimization technique. Here the SVM is accomplished for label classification.…”

Section: Literature Surveymentioning

confidence: 99%

Enhancing the Performance of an Intrusion Detection System Through Multi-Linear Dimensionality Reduction and Multi-Class SVM

Kumar¹,

Raju²,

Vardhan³

2018

IJIES

View full text Add to dashboard Cite

Abstract:With the huge development of the usage of computer over network and advancement in applications running on various platforms captures the attention towards network security. The Intrusion Detection System (IDS) plays a vital role in detecting anomalies and attacks in the network. Earlier approaches of IDS relied on Machine Learning (M L) techniques. Due to some limitations, a better approach is needed. A combination of Machine Learning techniques and data preprocessing is an effective approach for IDS. In this work, a new dimensionality reduction technique combined with the Multi-class SVM (Support Vector Machine) is proposed for intrusion detection. In the proposed model, Multi-Linear Dimensionality Reduction (ML-DR) is proposed as a feature extraction technique to reduce the dimension in order to shorten the training time. A Multi-class SVM (M-SVM) is used to detect whether the action is an attack or not. Here the Multi-class SVM is adopted to perform multi-attack classification in a layered fashion. Radial Basis Function Kernel is used as a SVM kernel. NSL-KDD data set is used for the performance evaluation of the proposed approach. The performance metrics such as classification accuracy, false alarm rate and the correlation coefficient are evaluated to measure its efficiency. In comparison with other detection approaches, the experimental results show that the proposed model outperforms the higher classification accuracy.

show abstract

Intrusion Detection in KDD99 Dataset using SVM-PSO and Feature Reduction with Information Gain

Cited by 56 publications

References 10 publications

Deep Abstraction and Weighted Feature Selection for Wi-Fi Impersonation Detection

Deep Abstraction and Weighted Feature Selection for Wi-Fi Impersonation Detection

AI-Based Two-Stage Intrusion Detection for Software Defined IoT Networks

Enhancing the Performance of an Intrusion Detection System Through Multi-Linear Dimensionality Reduction and Multi-Class SVM

Contact Info

Product

Resources

About