Intrusion detection and mitigation of attacks in microgrid using enhanced deep belief network

Durairaj, Danalakshmi; Kesavan, V. Thiruppathy; Mehbodniya, Abolfazl; Umar, Syed; Alam, Tanweer

doi:10.1080/15567036.2021.2023237

Cited by 13 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors tested the real-time traffic network through different numbers of deep learning algorithms to verify the effectiveness of the network architecture. Danalakshmi et al [25] proposed an IDS technique in which the Deep Belief Network is used by enhancing with a rule-based technique to improve the accuracy of the detection rate and reduce the false alarm rate as well. The authors concentrated only on False Data Injection and DoS attacks.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Intrusion Detection System for VANET Using Machine Learning and Deep Learning Approaches

Karthiga

Durairaj²,

Nawaz

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Detecting the attacks in Vehicular Ad hoc Network (VANET) system is very important to provide more secure and reliable communication between all vehicles in the system. In this article, an effective Intelligent Intrusion Detection System (IDS) is proposed using machine learning and deep learning approaches such as Adaptive Neuro Fuzzy Inference System (ANFIS) and Convolutional Neural Networks (CNN), respectively. The existing methods focus on detecting only the known attacks in VANET environment. This limitation is overcome by proposing the Intelligent IDS system using soft computing techniques. The proposed method consists of Known IDS (KIDS) and Unknown IDS (UIDS) modules, which detect both known attacks and unknown attacks. The KIDS module uses ANFIS classification module to detect the known malicious attacks, whereas the UIDS module uses a deep learning algorithm to detect the unknown attacks in VANET. Modified LeeNET (MLNET) architecture is proposed in this article to identify the type of unknown attacks. In this work, DoS attacks, Botnet attacks, PortScan attacks, and Brute Force attacks are detected using this hybrid learning algorithm. The proposed system obtains 96.9% of Pr, 98.3% of Se, 98.7% of Sp, and 98.6% of Acc and consumed 1.75 s for detecting the DoS attack on i-VANET dataset. The proposed system obtains 98.1% of Pr, 98.9% of Se, 98.1% of Sp, and 98.1% of Acc and consumed 0.95 s for detecting the Botnet attack. The proposed system obtains 98.7% of Pr, 99.1% of Se, 98.9% of Sp, and 99.2% of Acc and consumed 1.38 s for detecting the PortScan attack. The proposed system obtains 99.1of Pr, 97.8% of Se, 98.7% of Sp, and 98.5% of Acc and consumed 1.29 s for detecting the Brute Force attack. The developed methodology is tested on the real-time CIC-IDS 2017 dataset, and the experimental results are compared with other state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Intelligent Intrusion Detection System for VANET Using Machine Learning and Deep Learning Approaches

Karthiga

Durairaj²,

Nawaz

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…To handle sensors that examine the same data simultaneously in a centralized framework is quite tough. service (SaaS), platform as service (PaaS), and infrastructure as a service (IaaS) [40]. End users that use software for their day-to-day operations and are ready to pay a monthly subscription price make up the primary market for software as a service (SaaS).…”

Section: Literature Reviewmentioning

confidence: 99%

Internet of things: review, architecture and applications

Alam

2022

Comput Sci Inf Technol

View full text Add to dashboard Cite

Devices linked to the internet of things (IoT) may communicate with one another in several settings. Furthermore, rather of relying on an existing centralized system, users may develop their own network by using wireless capabilities. This kind of network is known as a wireless mobile ad hoc network. The mobile ad-hoc network (MANET) enables IoT devices to connect with one another in an unstructured networked environment. IoT devices may connect, establish linkages, and share data on a continuous basis. In this system, the cloud's purpose is to store and analyze data acquired from IoT devices. One of the most significant challenges in cloud computing has been identified as information security, and its resolution will result in an even bigger increase in cloud computing usage and popularity in the future. Finally, the goal of this project is to create a framework for facilitating communication between IoT devices in a Cloud and MANET context. Our major contribution is a ground-breaking research initiative that combines cloud computing with the MANET and connects the internet of things. This research might be used to the IoT in the future.

show abstract

Recent Applications of Artificial Intelligence for Sustainable Development in Smart Cities

Alam

Gupta²,

Qamar

et al. 2022

Studies in Computational Intelligence

View full text Add to dashboard Cite

Intrusion detection and mitigation of attacks in microgrid using enhanced deep belief network

Cited by 13 publications

References 56 publications

Intelligent Intrusion Detection System for VANET Using Machine Learning and Deep Learning Approaches

Intelligent Intrusion Detection System for VANET Using Machine Learning and Deep Learning Approaches

Internet of things: review, architecture and applications

Recent Applications of Artificial Intelligence for Sustainable Development in Smart Cities

Contact Info

Product

Resources

About