A security metric for the evaluation of collaborative intrusion detection systems in wireless sensor networks

Ramos, Alex; Lazar, Marcella; Filho, Raimir Holanda; Rodrigues, Joel J. P. C.

doi:10.1109/icc.2017.7997192

Cited by 8 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors examined the changes in the measurement scale and the formulation of criteria. In [50] the authors proposed the evaluation metrics to measure the effectiveness of collaborative decisions based on the likelihood of trust in collaborative decision-making processes. In [51] the author proposes a prioritization of alerts, which can be achieved by integrating several methods.…”

Section: Resultsmentioning

confidence: 99%

Wk-fnn design for detection of anomalies in the computer network traffic

Protic

Stanković

Antic

2022

Facta Univ Electron Energ

View full text Add to dashboard Cite

Anomaly-based intrusion detection systems identify abnormal computer network traffic based on deviations from the derived statistical model that describes the normal network behavior. The basic problem with anomaly detection is deciding what is considered normal. Supervised machine learning can be viewed as binary classification, since models are trained and tested on a data set containing a binary label to detect anomalies. Weighted k-Nearest Neighbor and Feedforward Neural Network are high-precision classifiers for decision-making. However, their decisions sometimes differ. In this paper, we present a WK-FNN hybrid model for the detection of the opposite decisions. It is shown that results can be improved with the xor bitwise operation. The sum of the binary ?ones? is used to decide whether additional alerts are activated or not.

show abstract

Section: Resultsmentioning

confidence: 99%

Wk-fnn design for detection of anomalies in the computer network traffic

Protic

Stanković

Antic

2022

Facta Univ Electron Energ

View full text Add to dashboard Cite

show abstract

“…As new preparations are developed to prevent or alleviate attacks, attackers are continually evolving new methods to circumvent these new procedures, designate various attack mechanisms, categories, the scope of attacks and their existing countermeasures [12]. Distributed Denial of Service Detection Approaches streams that know how to be second-hand to become conscious of the attacks near the source [13]. To balance this transaction, their dissertation, try to detect the attack in the transitional network.…”

Section: Related Workmentioning

confidence: 99%

An Efficient QOS Improvement Established on Unreasonable Investment, with a Half and Half Node Participation Clustering Approach in Mobile Ad Hoc Network

Ramani¹,

Sengottuvelan²

2018

IJET

View full text Add to dashboard Cite

Mobile ad hoc network (MANET) is characterized as a self-arranging foundationless system utilized for correspondence by wireless connections with the help of nodes. A MANET is suggested as the wireless system with autonomous nodes moving naturally concerning each other. Because of the different free moves of nodes, a lot of packet misfortune happens in transmitting the packet from source to goal. The danger of lousy node conduct is extraordinarily high. The unsecured unplanned system condition is started because of the progressive idea of systems and node portability. Likewise, the assignment of central administration is more confused in an improvised order. Because of the concept of free moving attributes, MANET faces disgraceful node collaboration. In this proposed work manages node collaboration to security issues like Unreasonable Investment, with a Half and Half Node Participation based Clustering approach (UIH 2 NPC) in MANET. The node collaboration among the nodes in MANET is enhanced by estimating the weightage of helpfulness of every node in the system. The assessment of node collaboration weightage identifies the external nodes contribution in the order. Execution assessments are done.

show abstract

“…The evaluation showed that their approach could quickly identify malicious nodes in real scenarios. For some other related works, we refer to [12][13][14][15][16][17][18].…”

Section: Trust-aware Mechanismmentioning

confidence: 99%

Investigating the Influence of Special On–Off Attacks on Challenge-Based Collaborative Intrusion Detection Networks

Meng

Kwok

2018

Future Internet

View full text Add to dashboard Cite

Abstract:Intrusions are becoming more complicated with the recent development of adversarial techniques. To boost the detection accuracy of a separate intrusion detector, the collaborative intrusion detection network (CIDN) has thus been developed by allowing intrusion detection system (IDS) nodes to exchange data with each other. Insider attacks are a great threat for such types of collaborative networks, where an attacker has the authorized access within the network. In literature, a challenge-based trust mechanism is effective at identifying malicious nodes by sending challenges. However, such mechanisms are heavily dependent on two assumptions, which would cause CIDNs to be vulnerable to advanced insider attacks in practice. In this work, we investigate the influence of advanced on-off attacks on challenge-based CIDNs, which can respond truthfully to one IDS node but behave maliciously to another IDS node. To evaluate the attack performance, we have conducted two experiments under a simulated and a real CIDN environment. The obtained results demonstrate that our designed attack is able to compromise the robustness of challenge-based CIDNs in practice; that is, some malicious nodes can behave untruthfully without a timely detection.

show abstract

A security metric for the evaluation of collaborative intrusion detection systems in wireless sensor networks

Cited by 8 publications

References 14 publications

Wk-fnn design for detection of anomalies in the computer network traffic

Wk-fnn design for detection of anomalies in the computer network traffic

An Efficient QOS Improvement Established on Unreasonable Investment, with a Half and Half Node Participation Clustering Approach in Mobile Ad Hoc Network

Investigating the Influence of Special On–Off Attacks on Challenge-Based Collaborative Intrusion Detection Networks

Contact Info

Product

Resources

About