Intelligent Intrusion Detection Based on Federated Learning for Edge-Assisted Internet of Things

Man, Dapeng; Zeng, Fanyi; Yang, Wu; Yu, Miao; Lv, Jiguang; Wang, Yijing

doi:10.1155/2021/9361348

Cited by 49 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For validation purposes, authors use a dataset containing traffic of a single IoT protocol. Moreover, recently a federated version of CNN was used by [28] for intrusion detection in IoT that is intended to reduce communication overhead. Other works, such as [29], are based on old industrial datasets that do not consider recent attacks from IIoT scenarios.…”

Section: Related Workmentioning

confidence: 99%

Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

Ruzafa-Alcazar

Fernandez-Saura

Marmol-Campos

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Federated Learning (FL) has attracted significant interest given its prominent advantages and applicability in many scenarios. However, it has been demonstrated that sharing updated gradients/weights during the training process can lead to privacy concerns. In the context of the Internet of Things (IoT), this can be exacerbated due to Intrusion Detection Systems (IDS), which are intended to detect security attacks by analyzing the devices' network traffic. Our work provides a comprehensive evaluation of Differential Privacy (DP) techniques, which are applied during the training of an FL-enabled IDS for Industrial IoT (IIoT). Unlike previous approaches, we deal with noniid data over the recent ToN IoT dataset and compare the accuracy obtained considering different privacy requirements and aggregation functions, namely FedAvg and the recently proposed Fed+. According to our evaluation, the use of Fed+ in our setting provides similar results even when noise is included in the federated training process.

show abstract

Section: Related Workmentioning

confidence: 99%

Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

Ruzafa-Alcazar

Fernandez-Saura

Marmol-Campos

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…Chatterjee et al [103] proposes a Probabilistic Hybrid Ensemble Classification (PHEC) model in the centralized and federated mode The study revealed that, compared with these modes, the FL mode performs better regarding privacy issues of the data and the problem of data processing in a single system. Man et al [104], presented a FEDACNN model based on CNN to solve the communication delay issue in the system by reducing communication rounds to 50%. Rajendran et al [105] proposed two FL models with ANN and LR for patient data privacy and security in healthcare systems.…”

Section: Federated Placement Ids For Iot Systemsmentioning

confidence: 99%

IoT Based Intrusion Detection Systems from The Perspective of Machine and Deep Learning: A Survey and Comparative Study

Ashraf¹,

Areed²,

Salem³

et al. 2022

Delta University Scientific Journal

View full text Add to dashboard Cite

The term "Internet of Things" (IoT) refers to a group of gadgets that are capable of connecting to the Internet in order to gather and share data. The growth of Internet connections and the arrival of new technologies like the Internet of Things (IoT) have increased the privacy and security threats associated with the introduction of various gadgets. In order to increase the detection of cyber-attacks, industries are increasing their research spending. Institutions choose wise testing and verification techniques by comparing the highest rates of accuracy. IoT use has been accelerating recently across a variety of industries, including health care, smart homes, intelligent transportation, smart cities, and smart grids. where technology researchers and developers started to take notice of the IoT possibilities. Unfortunately, the privacy and security concerns imposed on by energy restrictions and the scalability of IoT devices present the most significant challenge to IoT. Therefore, how to address the IoT's security and privacy challenges remains an essential issue in the field of information security. With a decentralized design, edge computing plays a vital role in enabling IoT devices to compute, make decisions, take actions, and push only pertinent information to the cloud. Since sensitive data is more readily available and can be used right away, the IDS performs better when employing machine learning (ML) and deep learning (DL) algorithms to identify and prevent various threats. In terms of technical limitations, this study classifies the current, recent research in IoT intrusion detection systems employing machine learning, deep learning, and edge computing architecture.

show abstract

“…Furthermore, it neglects unimportant parameter transmissions to the server with the help of an attention mechanism and greatly enhances the security performance with minimum communication overhead. The authors of [ 24 ] presented a federated-learning-assisted intelligent IDS model that exploits the FedACNN algorithm to detect intrusions in edge-enabled industrial IoT environments. It solves the issues associated with centralised machine learning models by transferring model parameters to the global server with high security instead of sending raw data.…”

Section: Related Workmentioning

confidence: 99%

Customised Intrusion Detection for an Industrial IoT Heterogeneous Network Based on Machine Learning Algorithms Called FTL-CID

Abosata

Al‐Rubaye

Tsourdos

2022

Sensors

View full text Add to dashboard Cite

Technological breakthroughs in the Internet of Things (IoT) easily promote smart lives for humans by connecting everything through the Internet. The de facto standardised IoT routing strategy is the routing protocol for low-power and lossy networks (RPL), which is applied in various heterogeneous IoT applications. Hence, the increase in reliance on the IoT requires focus on the security of the RPL protocol. The top defence layer is an intrusion detection system (IDS), and the heterogeneous characteristics of the IoT and variety of novel intrusions make the design of the RPL IDS significantly complex. Most existing IDS solutions are unified models and cannot detect novel RPL intrusions. Therefore, the RPL requires a customised global attack knowledge-based IDS model to identify both existing and novel intrusions in order to enhance its security. Federated transfer learning (FTL) is a trending topic that paves the way to designing a customised RPL-IoT IDS security model in a heterogeneous IoT environment. In this paper, we propose a federated-transfer-learning-assisted customised distributed IDS (FT-CID) model to detect RPL intrusion in a heterogeneous IoT. The design process of FT-CID includes three steps: dataset collection, FTL-assisted edge IDS learning, and intrusion detection. Initially, the central server initialises the FT-CID with a predefined learning model and observes the unique features of different RPL-IoTs to construct a local model. The experimental model generates an RPL-IIoT dataset with normal and abnormal traffic through simulation on the Contiki-NG OS. Secondly, the edge IDSs are trained using the local parameters and the globally shared parameters generated by the central server through federation and aggregation of different local parameters of various edges. Hence, transfer learning is exploited to update the server’s and edges’ local and global parameters based on relational knowledge. It also builds and customised IDS model with partial retraining through local learning based on globally shared server knowledge. Finally, the customised IDS in the FT-CID model enforces the detection of intrusions in heterogeneous IoT networks. Moreover, the FT-CID model accomplishes high RPL security by implicitly utilising the local and global parameters of different IoTs with the assistance of FTL. The FT-CID detects RPL intrusions with an accuracy of 85.52% in tests on a heterogeneous IoT network.

show abstract

Intelligent Intrusion Detection Based on Federated Learning for Edge-Assisted Internet of Things

Cited by 49 publications

References 27 publications

Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

IoT Based Intrusion Detection Systems from The Perspective of Machine and Deep Learning: A Survey and Comparative Study

Customised Intrusion Detection for an Industrial IoT Heterogeneous Network Based on Machine Learning Algorithms Called FTL-CID

Contact Info

Product

Resources

About