An extended evaluation on machine learning techniques for Denial-of-Service detection in Wireless Sensor Networks

Quincozes, Silvio E.; Kazienko, Juliano F.; Quincozes, Vagner E.

doi:10.1016/j.iot.2023.100684

Cited by 15 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Datasets should be expanded to include these types of attacks to better train ML algorithms [98]; -Benchmarking and Comparative Studies: A comprehensive evaluation and comparison of ML algorithms for IoT security, possibly facilitated by a unified benchmarking framework, could offer valuable insights into the strengths and weaknesses of different approaches [113,100,102]; -Lightweight Security Algorithms: As IoT devices are often constrained in terms of computational power and memory, there is a pressing need for security algorithms that are both effective and lightweight. Traditional security algorithms are generally not well-suited for these devices due to their high computational and memory demands [99,4].…”

Section: Research Opportunitiesmentioning

confidence: 99%

A survey on IoT application layer protocols, security challenges, and the role of explainable AI in IoT (XAIoT)

Quincozes,

Kazienko

et al. 2024

Int. J. Inf. Secur.

Self Cite

View full text Add to dashboard Cite

The Internet of Things (IoT) plays a fundamental role in contemporary society, necessitating an in-depth comprehension of its application layer protocols, intertwined technologies, security issues, and effective countermeasures. This survey delivers an exhaustive analysis of these protocols, emphasizing the escalating significance of Explainable Artificial Intelligence in IoT (XAIoT). To elucidate its practical implications, we conducted a case study examining a real-world scenario where XAIoT significantly bolstered IoT security. This case study demonstrated XAIoT's potential to enhance transparency and trustworthiness in IoT systems. Furthermore, the survey critically evaluates existing literature, pinpointing specific opportunities and gaps in the present state of IoT application layer security. For instance, our analysis revealed a pressing need for more robust security protocols and the integration of advanced machine learning techniques for anomaly detection in IoT applications. This survey, designed to provide a comprehensive perspective, seeks to stimulate additional innovation and research in the realm of secure and intelligent IoT applications. In doing so, it contributes to the ongoing dialogue on improving IoT security, offering valuable insights for researchers and practitioners alike.

show abstract

Section: Research Opportunitiesmentioning

confidence: 99%

A survey on IoT application layer protocols, security challenges, and the role of explainable AI in IoT (XAIoT)

Quincozes,

Kazienko

et al. 2024

Int. J. Inf. Secur.

Self Cite

View full text Add to dashboard Cite

show abstract

“…O ataque Grayhole consiste em uma categoria específica de ataques, sendo classificado como um tipo de ataque DoS [Quincozes et al 2023]. No Grayhole, o invasor obtém controle sobre um ou mais dispositivos na rede e, em seguida, descarta seletivamente os pacotes que trafegam por eles, em vez de encaminhá-los adequadamente.…”

Section: Ataque Grayholeunclassified

“…Dessa forma, o nó publicador atacante descarta deliberadamente uma parte dos pacotes de dados, sem enviá-los aos dispositivos assinantes. Como resultado, os dispositivos que assinaram o publicador não receberão todos os pacotes esperados [Quincozes et al 2023]. Outra possibilidade consiste no comprometimento de um nó assinante, o impedindo de processar todas as mensagens recebidas.…”

Section: Ataque Grayholeunclassified

“…Nesse contexto, uma das principais ameac ¸as consistem nos ataques de negac ¸ão de servic ¸o, do inglês Denial of Service (DoS). Dentre os ataques desta categoria, destaca-se o ataque de descarte seletivo de mensagens, conhecido como Grayhole [Quincozes et al 2023]. Nesse contexto, o uso de Sistemas de Detecc ¸ão de Intrusões, do inglês Intrusion Detection Systems (IDSs) se torna fundamental para a protec ¸ão das redes onde são transmitidas mensagens baseadas nesse padrão.…”

Section: Introduc ¸ãOunclassified

See 1 more Smart Citation

Modelagem e Detecção de Ataques Grayhole ao Protocolo GOOSE usando o Framework ERENO

Gonçalves,

Quincozes,

Quincozes

et al. 2023

Anais Do XXIII Simpósio Brasileiro De Segurança Da Informação E De Sistemas Computacionais (SBSeg 2023)

View full text Add to dashboard Cite

A crescente necessidade de reforçar a segurança cibernética na infraestrutura crítica, especificamente em subestações elétricas que se comunicam através do protocolo Generic Object Oriented Substation Event (GOOSE), requer técnicas efetivas de detecção e prevenção de ameaças. Esse protocolo é definido pelo padrão IEC-61850 e protege dispositivos físicos notificando eventos como faltas elétricas. Entretanto, a sua adoção abre brechas para a exploração de vulnerabilidades através de ataques cujas assinaturas precisam ser mapeadas. Destaca-se uma lacuna na literatura referente à falta de assinaturas do ataque Grayhole. Neste artigo, é proposta a modelagem e implementação de tal ataque ao protocolo GOOSE. Ademais, tal modelagem é incorporada ao ERENO, um framework para geração de datasets de intrusões. A eficácia do dataset resultante é validada através de cinco algoritmos de aprendizado de máquina, com destaque para o algoritmo J48 que obteve 90,68% de F1-Score.

show abstract

“…. The assessment of Denial-of-Service identification in WSNs that are using machine learning strategies is explained in Ref 164…”

mentioning

confidence: 99%

A comprehensive review of energy efficient routing protocols for query driven wireless sensor networks

Bekal,

Kumar,

Mane

et al. 2024

F1000Res

View full text Add to dashboard Cite

In this current era of communications and networking, The Internet of things plays the main role in the making of smart communication and networking. In this article, we have focused on the literature survey on wireless sensor networks which are energy efficient. Various standard protocols are reviewed along with some enhanced protocols which makes the network energy efficient. The comparison of the standard and enhanced protocols with respect to various applications in wireless sensor networks is thoroughly done in this article. The outcomes of the enhanced protocols are also briefly discussed. For easier analysis to future researchers, a comparative table which lists the enhanced protocols which are compared with standard counterparts along with the factors for energy efficiency of the protocols. This article also comments on the issues and challenges of the protocols which can be further analyzed for making the wireless sensor network more energy efficient.

show abstract

An extended evaluation on machine learning techniques for Denial-of-Service detection in Wireless Sensor Networks

Cited by 15 publications

References 25 publications

A survey on IoT application layer protocols, security challenges, and the role of explainable AI in IoT (XAIoT)

A survey on IoT application layer protocols, security challenges, and the role of explainable AI in IoT (XAIoT)

Modelagem e Detecção de Ataques Grayhole ao Protocolo GOOSE usando o Framework ERENO

A comprehensive review of energy efficient routing protocols for query driven wireless sensor networks

Contact Info

Product

Resources

About