CoWrap: An Approach of Feature Selection for Network Anomaly Detection

Ghosh, Anonnya; Ibrahim, Hussain Mohammed; Mohammad, Wasif; Nova, Farhana Chowdhury; Hasan, Amit; Rab, Raqeebir

doi:10.1007/978-3-030-99587-4_47

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As Internet usage increases, a growing number of threats are posing increasingly severe information security problems. There have been works of feature selection in network anomaly detection [22]. Despite their great potential, few IDS employ a class of algorithms known as generative adversarial networks.…”

Section: Discussionmentioning

confidence: 99%

Efficient Feature Selection On Adversarial Botnet Detection

Rab,

Bindu,

Sanjida

et al. 2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Botnet attacks now pose a significant hazard to the security and integrity of computer networks and information systems. However, due to technological advancements and the proliferation of malware, machine learning-based Intrusion Detection Systems (IDS) are incapable of protecting against such cyberattacks. IDS cannot detect novel bots because the vast majority of them are programmed systems. Keeping IDS upto-date with new malware varieties is, therefore, a crucial task. In this paper, we employ Generative Adversarial Networks (GANs) in which two neural networks compete and endeavor to outperform each other, which will serve as self-training for IDS. Our paper's primary objective is to develop an IDS capable of detecting novel malware with fewer attributes in real-time. To accomplish this, we present a method for feature selection that trains GAN models with a minimal subset of features so that the Generator can generate similar false bots with fewer features and the discriminator's ability to identify fake data improves. We used Pearson Correlation, the Wrapper method, and Mutual Information to select the best training model characteristics. The experimental evaluation suggests the GAN model in conjunction with Mutual Information is superior at detecting novel malware.

show abstract

Section: Discussionmentioning

confidence: 99%

Efficient Feature Selection On Adversarial Botnet Detection

Rab,

Bindu,

Sanjida

et al. 2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…-Feature selection helps in identifying the most significant features from the original set, reducing computational complexity, and improving the model's predictive performance [29]. The selection techniques can be classified into filter, wrapper, and embedded methods [22]. -Feature extraction techniques enable the generation of new features that capture important patterns and relationships in the data.…”

Section: Feature Engineeringmentioning

confidence: 99%

Feature Engineering Impact on Position Falsification Attacks Detection in Vehicular Ad-Hoc Network

Abdelkreem,

Hussein,

Tammam

2023

Preprint

View full text Add to dashboard Cite

The vehicular ad-hoc network (VANET) is a technology that enables vehicles to interact with each other and with the surrounding infrastructure. This technology aims to enhance road safety and alleviate traffic congestion. However, it is susceptible to various security attacks and concerns. Among these concerns, the position falsification attack is regarded as one of the most serious, in which, the malicious nodes tamper with their transmitted location. Thus, the development of effective misbehavior detection schemes capable of identifying such attacks is crucial. Many of these schemes employ machine learning techniques to classify vehicles based on the features of the exchanged information. Despite the relation between the performance of these systems and the features used to train them, the current understanding of this relation remains limited. In this paper, a comprehensive literature review is combined with a set of experiments to study the impact of feature engineering on the performance of position falsification attack detection in VANETs. The review is used to identify the key features and algorithms used in the literature. Then, various experiments were conducted using the VeReMi dataset, which is publicly available, and different machine learning algorithms to compare two feature sets: one comprising selected and derived features, and the other including all available features. The results of this study show a substantial improvement in the performance of the detectors achieved by employing feature engineering techniques, where the average accuracy of the experimented models is increased by 6.31% to 47.03% depending on the algorithm used.

show abstract

Efficient Feature Selection for IoT Security: A Comparative Analysis of Swarm Optimization Algorithms in Attack Detection

Mallidi,

Ramisetty

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

CoWrap: An Approach of Feature Selection for Network Anomaly Detection

Cited by 5 publications

References 9 publications

Efficient Feature Selection On Adversarial Botnet Detection

Efficient Feature Selection On Adversarial Botnet Detection

Feature Engineering Impact on Position Falsification Attacks Detection in Vehicular Ad-Hoc Network

Efficient Feature Selection for IoT Security: A Comparative Analysis of Swarm Optimization Algorithms in Attack Detection

Contact Info

Product

Resources

About