ML-based Detection of Rank and Blackhole Attacks in RPL Networks

Ioulianou, Philokypros P.; Shahandashti, Siamak F.

doi:10.1109/csndsp54353.2022.9908049

Cited by 7 publications

(8 citation statements)

References 14 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general the blackhole node controls every packet on that path [18]. Due to blackhole attack, retransimision rate is increase by child node and lead to DoS attack [40].…”

Section: Blackhole Attackmentioning

confidence: 99%

Blackhole attacks in internet of things networks: a review

Kamis

Yassin

Abdollah

et al. 2023

IJEECS

View full text Add to dashboard Cite

The internet of things (IoT) is one of data revolution area and is the following extraordinary mechanical jump after the internet. In terms of IoT, it is expected that electronic gadgets that are used on a regular basis would be connected to the current of the internet. IPv6 over low-power wireless personal area networks (6LoWPAN) is a one of IPv6 header pressure technology, and accordingly, it is vulnerable to attack. The IoT is a combination of devices with restricted resource assets like memory, battery power, and computational capability. To solve this, RPL or routing protocol for low power Lossy network is deploy by utilizing a distance vector scheme. One of denial of service (Dos) attack to RPL network is blackhole attack in which the assailant endeavors to become a parent by drawing in a critical volume of traffic to it and drop all packets. In this paper, we discuss research on numerous attacks and current protection methods, focusing on the blackhole attack. There is also discussion of challenge, open research issues and future perspectives in RPL security. Furthermore, research on blackhole attacks and specific detection technique proposed in the literature is also been presented.

show abstract

“…In general the blackhole node controls every packet on that path [18]. Due to blackhole attack, retransimision rate is increase by child node and lead to DoS attack [40].…”

Section: Blackhole Attackmentioning

confidence: 99%

Blackhole attacks in internet of things networks: a review

Kamis

Yassin

Abdollah

et al. 2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…As técnicas de AutoML ajudam as soluções a se adaptarem a diferentes tipos de ataques. Ioulianou et al (2022) utilizaram o processo AutoML para combater ataques de roteamento do tipo blackhole. No ataque blackhole, o invasor controla o nó malicioso e determina o descarte de todos os dados que recebe.…”

Section: Trabalhos Relacionadosunclassified

“…No ataque blackhole, o invasor controla o nó malicioso e determina o descarte de todos os dados que recebe. Ou seja, os nós legítimos tentam retransmitir os dados, mas, durante o ataque, o nó malicioso descarta todos os dados que recebe, prejudicando o correto funcionamento da rede [Ioulianou et al 2022]. Os autores verificaram que a solução proposta consegue encontrar diferentes arquiteturas de DL para diferentes conjuntos de dados.…”

Section: Trabalhos Relacionadosunclassified

“…Os autores verificaram que a solução proposta consegue encontrar diferentes arquiteturas de DL para diferentes conjuntos de dados. Ioulianou et al (2022) atingiram a acurácia de 97,91% classificando tráfego normal e malicioso para detectar o ataque blackhole. Contudo os autores não apresentam métricas complementares, como precisão e recall.…”

Section: Trabalhos Relacionadosunclassified

See 1 more Smart Citation

Um Sistema Autônomo para a Predição de Ataques de DDoS em Redes Locais e Internet

Brito¹,

Neira²,

Borges³

et al. 2023

Anais Do XXVIII Workshop De Gerência E Operação De Redes E Serviços (WGRS 2023)

View full text Add to dashboard Cite

Diante da constante evolução dos ataques de negação de serviço distribuído (DDoS), torna-se necessário o desenvolvimento de técnicas de predição para confrontar essas ameaças. A dissimulação dos ataques e o alto volume de tráfego de rede dificultam o seu reconhecimento. Portanto é importante identificar a preparação dos ataques para aumentar o tempo hábil de combatê-los. Este artigo apresenta um sistema autoadaptativo para a predição dos ataques DDoS. O sistema define automaticamente a melhor configuração da rede neural para distinguir a preparação do ataque DDoS do tráfego normal. Os resultados indicam que o sistema consegue predizer um ataque DDoS em 29 minutos antes do seu início com acurácia superior à literatura (97,89%).

show abstract

“…Traditionally, one of the popular methods of securing Internet-connected systems is to set up appropriate security mechanisms, such as intrusion detection systems (IDS), to be able to detect attacks that target systems and networks [11,12]. Some more recent solutions rely on deep learning techniques for IoT data analysis [13], cloud-based security mechanisms [14], cross-layer intrusion detection [15], reinforcement learning (RL) [16], and machine learning (ML)-based attack detection [17].…”

Section: Introductionmentioning

confidence: 99%

An Intrusion Detection System for RPL-Based IoT Networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

The Internet of Things (IoT) has become very popular during the last decade by providing new solutions to modern industry and to entire societies. At the same time, the rise of the industrial Internet of Things (IIoT) has provided various benefits by linking infrastructure around the world via sensors, machine learning, and data analytics. However, the security of IoT devices has been proven to be a major concern. Almost a decade ago, the IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL) was designed to handle routing in IoT and IIoT. Since then, numerous types of attacks on RPL have been published. In this paper, a novel intrusion detection system (IDS) is designed and implemented for RPL-based IoT. The objective is to perform an accurate and efficient detection of various types of routing and denial-of-service (DoS) attacks such as version number attack, blackhole attack, and grayhole attack, and different variations of flooding attacks such as Hello flood attack, DIS attack, and DAO insider attack. To achieve this, different detection strategies are combined, taking advantage of the strengths of each individual strategy. In addition, the proposed IDS is experimentally evaluated by performing a deep analysis of the aforementioned attacks in order to study the impact caused. This evaluation also estimates the accuracy and effectiveness of the IDS performance when confronted with the considered attacks. The obtained results show high detection accuracy. Furthermore, the overhead introduced in terms of CPU usage and power consumption is negligible. In particular, the CPU usage overhead is less than 2% in all cases, whereas the average power consumption increase is no more than 0.5%, which can be considered an insignificant impact on the overall resource utilisation.

show abstract

ML-based Detection of Rank and Blackhole Attacks in RPL Networks

Cited by 7 publications

References 14 publications

Blackhole attacks in internet of things networks: a review

Blackhole attacks in internet of things networks: a review

Um Sistema Autônomo para a Predição de Ataques de DDoS em Redes Locais e Internet

An Intrusion Detection System for RPL-Based IoT Networks

Contact Info

Product

Resources

About