A federated learning framework for cyberattack detection in vehicular sensor networks

Driss, Maha; Almomani, Iman; Huma, Zil e; Ahmad, Jawad

doi:10.1007/s40747-022-00705-w

Cited by 37 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple performance criteria, such as accuracy, precision, recall, F1-score, and training duration, were used to evaluate the proposed model. The testing results showed that the suggested FL method effectively detects attacks while protecting users' anonymity within VSNs [83].…”

Section: Analysis Of Federated Learning Based Existing Work In Iot Ne...mentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning Based Privacy Ensured Sensor Communication in IoT Networks: A Taxonomy, Threats and Attacks

et al. 2023

View full text Add to dashboard Cite

Our daily lives are significantly impacted by intelligent Internet of Things (IoT) application, services, IoT gadgets, and more intelligent industries. Artificial Intelligence (AI) is anticipated to have a substantial impact on training machine learning algorithms on IoT devices without sharing data. As data privacy has become a serious societal concern, Federated Learning (FL) has emerged as a hot research area for enabling the collaborative training of machine learning models across many smart IoT devices while adhering to privacy constraints. Although, FL is utilized for preserving privacy in IoT networks, but it is also facing some challenges such as privacy, effectiveness, and efficiency. In this article, a taxonomy of FL-based IoT systems is proposed and an analysis of related works on FL-based IoT systems is presented. Further, a comprehensive study of various types of threats, attacks, and frameworks is done. In addition to this, a taxonomy on privacy-preserving FL techniques for IoT networks is also devised. Finally, the study is concluded by highlighting the various open research challenges in FL-based IoT networks.

show abstract

Section: Analysis Of Federated Learning Based Existing Work In Iot Ne...mentioning

confidence: 99%

“…In 2022, Maha Driss et.al have developed FL-based system for the detection of cyberattack in Vehicular Sensor Networks (VSNs) [83]. To guarantee efficient attack detection, an ensembler unit is employed in conjunction with a set of GRU models.…”

Section: Analysis Of Federated Learning Based Existing Work In Iot Ne...mentioning

confidence: 99%

Federated Learning Based Privacy Ensured Sensor Communication in IoT Networks: A Taxonomy, Threats and Attacks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The model consists of two convolutional layers and three fully connected dense layers, which can improve performance and reduce computing power. Driss et al [25] proposed an attack detection framework for vehicle sensor networks based on federated learning. The scheme uses a group of gated recursive units and a signal group unit based on a random forest.…”

Section: Related Workmentioning

confidence: 99%

Internet of Things Intrusion Detection System Based on Convolutional Neural Network

Yin¹,

Shi²,

Dong³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In recent years, the Internet of Things (IoT) technology has developed by leaps and bounds. However, the large and heterogeneous network structure of IoT brings high management costs. In particular, the low cost of IoT devices exposes them to more serious security concerns. First, a convolutional neural network intrusion detection system for IoT devices is proposed. After cleaning and preprocessing the NSL-KDD dataset, this paper uses feature engineering methods to select appropriate features. Then, based on the combination of DCNN and machine learning, this paper designs a cloud-based loss function, which adopts a regularization method to prevent overfitting. The model consists of one input layer, two convolutional layers, two pooling layers and three fully connected layers and one output layer. Finally, a framework that can fully consider the user's privacy protection is proposed. The framework can only exchange model parameters or intermediate results without exchanging local individuals or sample data. This paper further builds a global model based on virtual fusion data, so as to achieve a balance between data privacy protection and data sharing computing. The performance indicators such as accuracy, precision, recall, F1 score, and AUC of the model are verified by simulation. The results show that the model is helpful in solving the problem that the IoT intrusion detection system cannot achieve high precision and low cost at the same time.

show abstract

“…By comparing this value with the existing related protocol described in Tables 7 and 8. The proposed method requires low communication cost than (Alexopoulos et al, 2018;Driss et al, 2022). According to Table 8, a distributed system has allowed the federated learning model to reach less computation process than the other classical methods.…”

Section: Computational Overheadmentioning

confidence: 99%

“…The host and network intrusion detection systems with blockchain technology in a detailed manner (Driss et al, 2022). The authors forecasted the usage of blockchain architecture in detecting the malicious nodes in huge CIDS networks and different categories of algorithms used in blockchain have been detailed and studied by Salam Al‐E'mari et al (2022).…”

Section: Related Workmentioning

confidence: 99%

Blockchain‐based multi‐layered federated extreme learning networks in connected vehicles

et al. 2022

View full text Add to dashboard Cite

Intelligent and networked vehicles help build an efficient vehicular network's infrastructure. The widespread use of electronic software exposes these networks to cyber‐attacks. Intrusion detection systems (IDS) are useful for preventing vehicle network assaults. IDS have been customized using machine and deep learning networks for greater real‐time performance. Current learning‐based intrusion detection systems demand substantial processing capabilities to train and update intricate training models in vehicular devices, resulting in decreased efficiency and ability to defend against assaults. This study presents Blockchain‐based Multi‐Layer Federated Extreme Learning Machines (MLFEM) enabled IDS (BEF‐IDS) for safe data transfers. The proposed IDS leverages federated learning to generate Multi‐Layered Extreme Learning Machines, which are offloaded to dispersed vehicular edge devices such as Road‐Side Units (RSU) and connected vehicles. This federated strategy decreases resource use without sacrificing security. Blockchain technology records and shares training models, assuring network security. Using real‐time data sets, the suggested algorithm's performance under different attack scenarios were extensively tested. The suggested method obtained 98% accuracy and Recall, 97.9% Precision, and 97.9% F1 Score performance, which suggests it's incredibly secure and costs very little to transmit.

show abstract

A federated learning framework for cyberattack detection in vehicular sensor networks

Cited by 37 publications

References 46 publications

Federated Learning Based Privacy Ensured Sensor Communication in IoT Networks: A Taxonomy, Threats and Attacks

Federated Learning Based Privacy Ensured Sensor Communication in IoT Networks: A Taxonomy, Threats and Attacks

Internet of Things Intrusion Detection System Based on Convolutional Neural Network

Blockchain‐based multi‐layered federated extreme learning networks in connected vehicles

Contact Info

Product

Resources

About