An Effective IDS for MANET Using Forward Feature Selection and Classification Algorithms

Visumathi, J.; Shunmuganathan, K. L.

doi:10.1016/j.proeng.2012.06.330

Cited by 6 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their framework, N supervised classifiers were built in N prepared clusters so each classifier met a relatively easy learning problem. Feature selection algorithms or the descending dimension algorithms were also usually used before supervised learning algorithms to increase the efficiency of training [11], [12]. In recent years, deep learning methods such as CNN and SAE have been tried to be applied in intrusion detection system.…”

Section: Related Workmentioning

confidence: 99%

MSML: A Novel Multilevel Semi-Supervised Machine Learning Framework for Intrusion Detection System

Yao

Zhang

et al. 2019

IEEE Internet Things J.

101

View full text Add to dashboard Cite

Intrusion detection technology has received increasing attention in recent years. Many researchers have proposed various intrusion detection systems using machine learning methods. However, there are two noteworthy factors affecting the robustness of the model. One is the severe imbalance of network traffic in different categories, and the other is the non-identical distribution between training set and test set in feature space. This paper presents a multi-level intrusion detection model framework named MSML to address these issues. The MSML framework includes four modules: pure cluster extraction, pattern discovery, fine-grained classification and model updating. In the pure cluster module, we introduce an concept of "pure cluster" and propose a hierarchical semi-supervised k-means algorithm (HSK-means) with an aim to find out all the pure clusters. In the pattern discovery module, we define the "unknown pattern and apply cluster based method aiming to find those unknown patterns. Then a test sample is sentenced to labeled known pattern or unlabeled unknown pattern. The fine-grained classification module can achieves fine-grained classification for those unknown pattern samples. The model updating module provides a mechanism for retraining. KDDCUP99 dataset is applied to evaluate MSML. Experimental results show that MSML is superior to other existing intrusion detection models in terms of overall accuracy, F1 score and unknown pattern recognition capability.

show abstract

Section: Related Workmentioning

confidence: 99%

MSML: A Novel Multilevel Semi-Supervised Machine Learning Framework for Intrusion Detection System

Yao

Zhang

et al. 2019

IEEE Internet Things J.

101

View full text Add to dashboard Cite

show abstract

“…Simulations have shown that the proposed system performs well under different attack scenarios with low network degradations. Another intrusion detection system was proposed in [42]. The proposed intrusion detection system was based on forward feature selection and classification algorithms.…”

Section: Counter Measuresmentioning

confidence: 99%

MANET security: A survey

Alani

2014

2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014)

View full text Add to dashboard Cite

Mobile Ad hoc Networks are being adopted in more and more applications in our daily life. Mobile computing and mobile ad hoc networks in particular have become a daily need. As mobile ad hoc networks have been target for many attacks, the security of these networks has become an essential part of their existence. This paper provides a review of the current threats and how these threats are mitigated. The paper also discusses common attacks on mobile ad hoc networks and classifies these attacks in various classification types. The paper also discusses various countermeasures to mitigate the risks of attacks.

show abstract

“…Most of today’s applications are real-time applications, which need to deliver data at the right time and with the use of available resources. Any activity in a computer system that violates the security or availability of resources can be classified as an intrusion [ 1 ]. Preventive and reactive approaches are applied by most security solutions, in order to protect MANET’s routing protocol, services and applications.…”

Section: Introductionmentioning

confidence: 99%

FSM-F: Finite State Machine Based Framework for Denial of Service and Intrusion Detection in MANET

2016

View full text Add to dashboard Cite

Due to the continuous advancements in wireless communication in terms of quality of communication and affordability of the technology, the application area of Mobile Adhoc Networks (MANETs) significantly growing particularly in military and disaster management. Considering the sensitivity of the application areas, security in terms of detection of Denial of Service (DoS) and intrusion has become prime concern in research and development in the area. The security systems suggested in the past has state recognition problem where the system is not able to accurately identify the actual state of the network nodes due to the absence of clear definition of states of the nodes. In this context, this paper proposes a framework based on Finite State Machine (FSM) for denial of service and intrusion detection in MANETs. In particular, an Interruption Detection system for Adhoc On-demand Distance Vector (ID-AODV) protocol is presented based on finite state machine. The packet dropping and sequence number attacks are closely investigated and detection systems for both types of attacks are designed. The major functional modules of ID-AODV includes network monitoring system, finite state machine and attack detection model. Simulations are carried out in network simulator NS-2 to evaluate the performance of the proposed framework. A comparative evaluation of the performance is also performed with the state-of-the-art techniques: RIDAN and AODV. The performance evaluations attest the benefits of proposed framework in terms of providing better security for denial of service and intrusion detection attacks.

show abstract

An Effective IDS for MANET Using Forward Feature Selection and Classification Algorithms

Cited by 6 publications

References 14 publications

MSML: A Novel Multilevel Semi-Supervised Machine Learning Framework for Intrusion Detection System

MSML: A Novel Multilevel Semi-Supervised Machine Learning Framework for Intrusion Detection System

MANET security: A survey

FSM-F: Finite State Machine Based Framework for Denial of Service and Intrusion Detection in MANET

Contact Info

Product

Resources

About