Implementation of Network Intrusion Detection System Using Artificial Intelligence: Survey

Maidamwar, Priya; Bartere, Mahip M.; Lokulwar, Prasad P.

doi:10.1007/978-981-16-6407-6_18

Cited by 16 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nakkeeran and Mathi [ 122 ] provided a framework for end-to-end IoT sensor and device solutions and a detection method for identifying suspicious and anomalous network behaviour through cross-layer analysis. Maidamwar et al [ 124 ] reviewed the design of an intrusion detection framework for the WSN-based IoT, which they described as being able to increase confidence in the reliability of IoT networks and contain network intrusions. Raimundo and Rosário [ 125 ] filled a gap in the research on cybersecurity risks in the IoT domain by discussing the existing solutions and cyberthreats in the industrial Internet of Things (IIoT), based on a literature review.…”

Section: Cybersecurity In Smart Citiesmentioning

confidence: 99%

Cybersecurity and Cyber Forensics for Smart Cities: A Comprehensive Literature Review and Survey

Kim

Alshenaifi

Ramachandran

et al. 2023

Sensors

View full text Add to dashboard Cite

Smart technologies, such as the Internet of Things (IoT), cloud computing, and artificial intelligence (AI), are being adopted in cities and transforming them into smart cities. In smart cities, various network technologies, such as the Internet and IoT, are combined to exchange real-time information, making the everyday lives of their residents more convenient. However, there is a lack of systematic research on cybersecurity and cyber forensics in smart cities. This paper presents a comprehensive review and survey of cybersecurity and cyber forensics for smart cities. We analysed 154 papers that were published from 2015 to 2022 and proposed a new framework based on a decade of related research papers. We identified four major areas and eleven sub-areas for smart cities. We found that smart homes and the IoT were the most active research areas within the cybersecurity field. Additionally, we found that research on cyber forensics for smart cities was relatively limited compared to that on cybersecurity. Since 2020, there have been many studies on the IoT (which is a technological component of smart cities) that have utilized machine learning and deep learning. Due to the transmission of large-scale data through IoT devices in smart cities, ML and DL are expected to continue playing critical roles in smart city research.

show abstract

Section: Cybersecurity In Smart Citiesmentioning

confidence: 99%

Cybersecurity and Cyber Forensics for Smart Cities: A Comprehensive Literature Review and Survey

Kim

Alshenaifi

Ramachandran

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…With the rise of the Internet of Things (IoT), the number and diversity of threats to the security of computer networks are increasing [1]. Thus, detecting attacks and protecting the network has become a very challenging task for security mechanisms, such as the Intrusion Detection System (IDS) and Intrusion Prevention System (IPS) [2]. The main challenges faced in monitoring and preventing these attacks are the large amount of data generated by the IoT devices and the costs and time of analysis and processing involved.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, it is not only relevant to detect malicious activity on the network but it is also crucial to identify and classify the attacks. According to the specific type of attack identified, various actions can be taken to stop and prevent the future occurrence of this attack [2].…”

Section: Introductionmentioning

confidence: 99%

OMINACS: Online ML-Based IoT Network Attack Detection and Classification System

Abreu,

Abelém

2023

Preprint

View full text Add to dashboard Cite

Several Machine Learning (ML) methodologies have been proposed to improve security in Internet Of Things (IoT) networks and reduce the damage caused by the action of malicious agents. However, detecting and classifying attacks with high accuracy and precision is still a major challenge. This paper proposes an online attack detection and network traffic classification system, which combines stream Machine Learning, Deep Learning, and Ensemble Learning technique. Using multiple stages of data analysis, the system can detect the presence of malicious traffic flows and classify them according to the type of attack they represent. Furthermore, we show how to implement this system both in an IoT network and from an ML point of view. The system was evaluated in three IoT network security datasets, in which it obtained accuracy and precision above 90% with a reduced false alarm rate.

show abstract

“…No cenário atual, cresce cada vez mais a quantidade e diversidade de ameac ¸as à seguranc ¸a das redes de computadores [Liang and Kim 2021]. Assim, detectar ataques e proteger a rede tem se tornado uma tarefa muito desafiadora para os mecanismos de seguranc ¸a, como Sistema de Detecc ¸ão de Intrusão (Intrusion Detection System -IDS) e Sistema de Prevenc ¸ão de Intrusão (Intrusion Prevention System -IPS) [Maidamwar et al 2022]. Os principais desafios enfrentados no monitoramento e prevenc ¸ão de ataques são a grande quantidade de dados e os custos e tempo da análise e do processamento envolvidos.…”

Section: Introduc ¸ãOunclassified

“…Além disso, é importante não apenas detectar a ocorrência de uma ac ¸ão maliciosa na rede, mas também conseguir caracterizar e classificar os ataques de forma correta. De acordo com o tipo específico de ataque identificado, pode-se tomar decisões e ac ¸ões distintas nas redes buscando interromper o ataque em andamento e prevenir a ocorrência futura deste ataque [Maidamwar et al 2022].…”

Section: Introduc ¸ãOunclassified

Sistema Híbrido e On-line de Detecção e Classificação de Tráfego Malicioso

Abreu¹,

Abelem²

2022

Anais Do XL Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2022)

View full text Add to dashboard Cite

Diversas metodologias de Aprendizado de Máquina têm sido propostas para melhorar a segurança em redes de computadores e reduzir os danos causados pela ação de agentes maliciosos. Entretanto, detectar e classificar ataques de forma acurada e precisa ainda é um grande desafio nas redes atuais. Este artigo propõe um sistema on-line de detecção de ataques e classificação de tráfego de rede, que combina de forma híbrida Aprendizado de Máquina por Stream, o Aprendizado Profundo e a técnica Ensemble. Utilizando múltiplos estágios de análise dos dados, o sistema detecta a presença de fluxos de tráfegos maliciosos e classifica-os de acordo com o tipo de ataque que eles representam. O sistema foi avaliado em três bases de dados de referência em segurança, nas quais obteve acurácia e precisão acima de 90%, com taxa de falso alarme reduzida.

show abstract

Implementation of Network Intrusion Detection System Using Artificial Intelligence: Survey

Cited by 16 publications

References 28 publications

Cybersecurity and Cyber Forensics for Smart Cities: A Comprehensive Literature Review and Survey

Cybersecurity and Cyber Forensics for Smart Cities: A Comprehensive Literature Review and Survey

OMINACS: Online ML-Based IoT Network Attack Detection and Classification System

Sistema Híbrido e On-line de Detecção e Classificação de Tráfego Malicioso

Contact Info

Product

Resources

About