ELPC-Trust Framework for Wireless Sensor Networks

Dharini, N.; Duraipandian, N.; Katiravan, Jeevaa

doi:10.1007/s11277-020-07288-0

Cited by 11 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of time taken to build model from table 5 the time taken to build random tree was the lowest when compared to all the algorithms. In our evaluation of Mirai botnet performance across 9 IoT devices, we compared the effectiveness of utilizing 35 and 5 features, as presented in figures (8-13) and figures (14)(15)(16)(17)(18)(19). Random tree, random forest, and random committee consistently demonstrated strong performance across all 9 devices, with random committee achieving the highest accuracy of 99.99% and Hoeffding tree registering the lowest accuracy of 74.56%.…”

Section: Perforomance Metrics For 9 Iot Devices For Both Bashlite And...mentioning

confidence: 99%

“…Versatility: Ensemble methods can be applied to a wide range of machine learning tasks, including classification, regression, and clustering. Our previous works [13][14][15] exemplifies the usage of significant network parameters such as energy, packet count etc as the most distinguishing factors to detect attacks in wireless network [16,17]. Thus in this proposed work, we utilize ensemble classifiers to enhance efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Botnet Attack Detection in IoT Devices using Ensemble Classifiers with Reduced Feature Space

Katiravan,

S.P

2024

Int. Res. J. multidiscip. Technovation

Self Cite

View full text Add to dashboard Cite

The Internet of Things (IoT) is an advancing important technology offers multiple perks, such as webcams, baby monitors, room temperature controllers, smart security cameras and intelligent home automations resulting in the creation of intelligent settings that greatly simplify daily living. However, there are cybersecurity dangers associated with IoT devices due to their lack of protection. For example, Internet of Things botnets have become a major risk. IoT has been a boon for attackers to perform malicious attacks like information theft, DDoS, sending junk data to disrupt networks. IoT devices face serious security issues, from having default weak and common passwords, and a lack of security, rarely and poorly monitored, to having open access to management systems, always connected to the internet. In this paper, we used the N-BaIoT dataset which includes datasets of 9 IoT devices infected with 2 Bot viruses Mirai and Bashlite, where each botnet has 5 sub-attacks and the benign datasets of 9 devices. An analysis with the N-BaIoT dataset which initially had 115 features were reduced to 35 features by using manual reduction and further reduced to single feature in 5-time instances equivalent to 5 features using heat map. We then classified the sub-attacks of 2 botnets and benign of 9 IoT devices by using 7 Machine Learning based classifiers in the Weka tool and Python and compared our results with the manually reduced 35 Features and Heat map based 5 features. Performance metrics like correctly classified, incorrectly classified instances and time taken to build the model were evaluated to verify the proposed work. We found out that over 3 ensemble machine learning classifiers performed extremely well with 99 % accuracies for all devices. In order to verify the logic of our work we tried implementing our proposed model in a different dataset with 3 ensemble classifiers and were able to achieve high detection rates.

show abstract

Section: Perforomance Metrics For 9 Iot Devices For Both Bashlite And...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Botnet Attack Detection in IoT Devices using Ensemble Classifiers with Reduced Feature Space

Katiravan,

S.P

2024

Int. Res. J. multidiscip. Technovation

Self Cite

View full text Add to dashboard Cite

show abstract

“…[32] proposed a trustable and secure routing scheme using a twostage security mechanism based on active trust and a Cuckoo search algorithm to protect routes from black hole attacks and selective forwarding attacks. [33] proposed Energy-Lifetime-Packet Count Trust framework for attack categorization based on Energy, Packet Count, and Z scores and for calculation of the nodes' trust values. Trust scores are computed based on the intensity of the attack in terms of their network performance degradation.…”

Section: B Reputation-based Schemesmentioning

confidence: 99%

“…But, in fact, the abnormal information may come from the harsh environment even without channel contending collision. The reputationbased detection schemes [23][24][25][26][27][28][29][30][31][32][33] differentiate the malicious nodes from normal nodes according to the nodes' reputation based on the nodes' forwarding behaviors. In these schemes, the threshold values depend on the estimation of their channel quality.…”

Section: Introductionmentioning

confidence: 99%

Employ DBSCAN and Neighbor Voting to Screen Selective Forwarding Attack Under Variable Environment in Event-Driven Wireless Sensor Networks

Liu

2021

IEEE Access

View full text Add to dashboard Cite

In the event-driven wireless sensor networks (EWSNs), the event of interests occurs irregularly and at random in the network. Then, sensor nodes near the event sense the event and send out data packets of the event. Next, router nodes (RNs) forward those packets to the sink node (SN) by multi-hop communications. Compromised RNs would become malicious and launch selective forwarding attacks by dropping part of or all the packets from other nodes. On the other hand, a harsh environment makes the channel poor, so the routing nodes under a harsh environment have low packet forwarding rates because they sometimes have to give up forwarding the current packets after many tries to forward them due to poor channel. If the malicious nodes' forwarding rates become close to those of nodes under a harsh environment, the schemes based on packet forwarding rates for detecting selective forwarding attack may fail because they cannot differentiate the low data packet forwarding rates resulting from the malicious behaviors or harsh environment. To solve this problem, we provide a combined scheme for detecting selective forwarding attack in wireless sensor networks (WSNs) under harsh environments. This scheme employs a data clustering algorithm (DCA) to screen the malicious nodes out by clustering their cumulative forwarding rates (CFRs) and designs a voting decision method to protect the nodes under a harsh environment from being judged as malicious nodes. The simulation results show that our scheme has a low false detection rate (FDR) of 1% and a low missed detection rate (MDR) of 5% respectively with negligible energy consumption in WSNs under a local variable harsh environment.INDEX TERMS event-driven wireless sensor networks, selective forwarding attack, cumulative forwarding rate, data clustering algorithm

show abstract

“…An approach of intrusion detection-based available network routing for a mobile ad-hoc network, which can decrease both the packet loss rate and the end-to-end delay, was introduced in Sivakumar et al [17]. An intrusion detection cum trust-based framework for attack detection and network reliability maintenance was proposed [18]. The WSNs have been widely applied in many fields, including environmental monitoring and water quality monitoring.…”

Section: Related Workmentioning

confidence: 99%

Trust Management-Based Service Recovery and Attack Prevention in MANET

Nivedita¹,

Nandhagopal²

2021

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The mobile ad-hoc network (MANET) output is critically impaired by the versatility and resource constraint of nodes. Node mobility affects connection reliability, and node resource constraints can lead to congestion, which makes the design of a routing MANET protocol with quality of service (QoS) very difficult. An adaptive clustering reputation model (ACRM) method is proposed to improve energy efficiency with a cluster-based framework. The proposed framework is employed to overcome the problems of data protection, privacy, and policy. The proposed ACRM-MRT approach that includes direct and indirect node trust computation is introduced along with the master recovery timer (MRT) for achieving an efficient service recovery process, and its service recovery time is calculated through the service execution process. During data transmission in MANET, various types of attacks can occur, of which the Sybil attack is the most dangerous. To address this problem, this paper proposed a method for the detection and prevention of Sybil attacks using a resilient scheme. The proposed method can improve system energy efficiency and address security, safety, and privacy issues of wireless network applications. Finally, the performance of the proposed method is evaluated regarding the time delay, throughput, energy efficiency, control overhead, and detection rate. The simulation results show that the proposed ACRM-MRT method can effectively improve the time delay, throughput, energy efficiency, control overhead, and detection rate compared to the existing methods. Topological change adaptive ad-hoc on-demand multi-path distance vector (TA-AOMDV)and ad-hoc on-demand multi-path distance vector (AOMDV) are simulated on the NS2 platform for the data rate in the range of 4-40 kbps and the number of nodes in the range of 10-100. The proposed method can reduce the service recovery time in the case of faults during service execution and can be used in real-time applications traffics since it is mostly affected by failure through the occurrence of delay and loss of packets.

show abstract

ELPC-Trust Framework for Wireless Sensor Networks

Cited by 11 publications

References 16 publications

Botnet Attack Detection in IoT Devices using Ensemble Classifiers with Reduced Feature Space

Botnet Attack Detection in IoT Devices using Ensemble Classifiers with Reduced Feature Space

Employ DBSCAN and Neighbor Voting to Screen Selective Forwarding Attack Under Variable Environment in Event-Driven Wireless Sensor Networks

Trust Management-Based Service Recovery and Attack Prevention in MANET

Contact Info

Product

Resources

About