WSN-BFSF: A New Data Set for Attacks Detection in Wireless Sensor Networks

Dener, Murat; Okur, Celil; Al, Samed; Orman, Abdullah

doi:10.1109/jiot.2023.3292209

Cited by 7 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper proposes a lightweight Challenge-Response Authentication-based technique called CRA-RPL to secure RPL against DDAO attacks, which has been successfully implemented and validated in experimental settings. The paper [22] highlights the increasing utilization of Wireless Sensor Networks (WSN) and the corresponding rise in attacks on these networks. The use of learning models in WSN, specifically for attack detection, has shown to yield highly accurate results compared to classical detection methods.…”

Section: Related Workmentioning

confidence: 99%

Identity Based Authentication Scheme (IAS) for Securing WSN Based Internet of Things

Asha Ambhaikar

2024

jes

View full text Add to dashboard Cite

The growing number of connected devices in IoT networks has raised security concerns. These networks face unique challenges, including limited resources, lack of standardized security protocols, and diverse devices and applications. Identity-based authentication is needed to address these threats and limitations. Implementing a multi-factor authentication system can enhance security and protect sensitive information from unauthorized access. The proposed Identity Based Authentication (IAS) scheme is implemented using the NS-2 simulator to address security challenges in IoT networks. Each node is assigned a unique identity for authentication, ensuring only authorized access and preventing security breaches. The IAS scheme enhances IoT network security by verifying node identities. Two scenarios are considered to evaluate the scalability and interoperability of the IAS scheme. The first scenario involves a random environment, assessing performance in real-world settings with varying device densities and network conditions. The second scenario involves a cluster-based environment, providing insights into the scheme's functionality and efficiency. By examining both scenarios, this research aims to provide a comprehensive understanding of how the authentication scheme performs in different deployment scenarios. The findings highlight the importance of selecting the appropriate authentication scheme based on the specific network environment and requirements. The superiority of the IAS authentication scheme suggests its potential for widespread adoption and implementation in various network scenarios over other authentication schemes.

show abstract

Section: Related Workmentioning

confidence: 99%

Identity Based Authentication Scheme (IAS) for Securing WSN Based Internet of Things

Asha Ambhaikar

2024

jes

View full text Add to dashboard Cite

show abstract

“…Subsequently, in 2023, Dener et al. [ 22 ] introduced a novel dataset, WSN-BFSF, specifically designed to detect DoS attacks in WSNs. Their investigation involved the evaluation of four ML and eight deep-learning models, yielding notable outcomes.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Intrusion Detection in Wireless Sensor Networks Using a GSWO-CatBoost Approach

Nguyen,

Vo,

Yoo

2024

Sensors

View full text Add to dashboard Cite

Intrusion detection systems (IDSs) in wireless sensor networks (WSNs) rely heavily on effective feature selection (FS) for enhanced efficacy. This study proposes a novel approach called Genetic Sacrificial Whale Optimization (GSWO) to address the limitations of conventional methods. GSWO combines a genetic algorithm (GA) and whale optimization algorithms (WOA) modified by applying a new three-population division strategy with a proposed conditional inherited choice (CIC) to overcome premature convergence in WOA. The proposed approach achieves a balance between exploration and exploitation and enhances global search abilities. Additionally, the CatBoost model is employed for classification, effectively handling categorical data with complex patterns. A new technique for fine-tuning CatBoost’s hyperparameters is introduced, using effective quantization and the GSWO strategy. Extensive experimentation on various datasets demonstrates the superiority of GSWO-CatBoost, achieving higher accuracy rates on the WSN-DS, WSNBFSF, NSL-KDD, and CICIDS2017 datasets than the existing approaches. The comprehensive evaluations highlight the real-time applicability and accuracy of the proposed method across diverse data sources, including specialized WSN datasets and established benchmarks. Specifically, our GSWO-CatBoost method has an inference time nearly 100 times faster than deep learning methods while achieving high accuracy rates of 99.65%, 99.99%, 99.76%, and 99.74% for WSN-DS, WSNBFSF, NSL-KDD, and CICIDS2017, respectively.

show abstract

“…Network traffic routing was carried out with AODV protocol based in sel-synchronization and does not require a fixed infrastructure. Datasets [26] used consists of 16 features sizes and 312106 rows. It's main goal is to detect DoS attacks in a wireless sensor networks by analysing the traffic with 4 different machine learning [24] (Random Forest, Decision Tree, Naïve Bayes and Logistic Regression) and 8 different deep learning models [24] (Multilayer Perception "MLP", Convolutional Neural Network "CNN", long shortterm memory "LSTM", Gated Recurrent Unit "GRU", CNN -LSTM, LSTM-CNN, CNN -GRU and GRU -CNN).…”

Section: -Experimentmentioning

confidence: 99%

Proposed Method for Detecting Active Attacks in Wireless Sensor Network Using Machine Learning and Hash Cryptographic Function

FARES,

HAJRAOUI,

HAJRAOUI

2023

IJASER

View full text Add to dashboard Cite

Network monitoring and analysis has taken primordial role to understand the functioning of the internet and prevent it from any future probable attacks. Many publications treated the topic of the security as an interesting research domain. Due to the importance and the different applications of wireless sensor networks, the research of finding security solutions is always up but their limited resources (energy consumption, CPU capacity, limited memory…) make the application of classical protocols of security like cryptography, almost impossible. Therefore, recently machine learning is a new field which gets the interest of the majority of researchers. The solutions for providing security services conveyable of in this type of network, are proposed. In this paper we focus in the monitoring of wireless sensor network using machine learning as an intrusion detection system. We address in particular to active attacks. Because of the limitation of machine learning and to provide a high protection against attack we proposed a hash cryptographic function in order to protect the authenticity of information. Our interesting contribution aims three important axes of security: confidentiality, integrity and authentication.

show abstract

WSN-BFSF: A New Data Set for Attacks Detection in Wireless Sensor Networks

Cited by 7 publications

References 38 publications

Identity Based Authentication Scheme (IAS) for Securing WSN Based Internet of Things

Identity Based Authentication Scheme (IAS) for Securing WSN Based Internet of Things

Enhancing Intrusion Detection in Wireless Sensor Networks Using a GSWO-CatBoost Approach

Proposed Method for Detecting Active Attacks in Wireless Sensor Network Using Machine Learning and Hash Cryptographic Function

Contact Info

Product

Resources

About