HBFL: A hierarchical blockchain-based federated learning framework for collaborative IoT intrusion detection

Sarhan, Mohanad; Lo, Wai Weng; Layeghy, Siamak; Portmann, Marius

doi:10.1016/j.compeleceng.2022.108379

Cited by 44 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, we also compare and contrast experimental data to show that BCEAD has better detection performance than previous methods. Sarhan et al [25] presented a federated learning architecture built on a blockchain-based hierarchy to ensure that collaborative IoT intrusion detection is safe and private. The proposed machine learning-based intrusion detection system employs a federated learning architecture with a hierarchical structure to safeguard the confidentiality of the training and company information.…”

Section: Related Workmentioning

confidence: 99%

“…Machine learning models are statistical algorithms with the ability to infer meaningful insights about future data by learning complex patterns in existing data [25]. These ML models are designed using a training procedure in which the learning models glean relevant meanings from the accessible data logs.…”

Section: Sensor Nodesmentioning

confidence: 99%

“…This shows that the proposed method achieves better classification accuracy. Sarhan et al [25] proposed a hierarchical blockchain-based federated learning (HBFL) for a secure collaborated intrusion detection system in IoT-based wireless sensor networks as shown in Figure 14(a). The scheme achieves an average detection accuracy of 99.71% using a benchmark dataset UNSW-NB15 containing various classes of attacks.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

Gebremariam

Panda

Indu

2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Wireless sensor networks are the core of the Internet of Things and are used in healthcare, locations, the military, and security. Threats to the security of wireless sensor networks built on the Internet of Things (IoT-WSNs) can come from a variety of sources. This study proposes secure attack localization and detection in IoT-WSNs to improve security and service delivery. The technique used blockchain-based cascade encryption and trust evaluation in a hierarchical design to generate blockchain trust values before beacon nodes broadcast data to the base station. Simulation results reveal that cascading encryption and feature assessment measure the trust value of nodes by rewarding each other for service provisioning and trust by removing malicious nodes that reduce localization accuracy and quality of service in the network. Federated machine learning improves data security and transmission by merging raw device data and placing malicious threats in the blockchain. Malicious nodes are classified through federated learning. Federated learning combines hybrid random forest, gradient boost, ensemble learning, K -means clustering, and support vector machine approaches to classify harmful nodes via a feature assessment process. Comparing the proposed system to current ones shows an average detection and classification accuracy of 100% for binary and 99.95% for multiclass. This demonstrates that the suggested approach works well for large-scale IoT-WSNs, both in terms of performance and security, when utilizing heterogeneous wireless senor networks for the providing of secure services.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Sensor Nodesmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

Gebremariam

Panda

Indu

2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Protection of physical components, applications, network connections and data are managed by this process. This process is effectively beneficial for an organisation to ensure integrity, availability and confidentiality of IoT ecosystems [18]. High volume of flaws discovers in IoT framework on a daily basis to maintain security challenges.…”

Section: Major Concerns Of Industrial Iot Securitymentioning

confidence: 99%

A Study into the Security Issues and Countermeasures for the Industrial Internet of Things (IIOT)

Baldelovar¹,

G²

2022

TTITCCR

View full text Add to dashboard Cite

Industrial internet of things are essential factors for an organisation to maintain relevant work strategy. In this study, several types of security issues and countermeasures for IIOT are discussed critically. Various kinds of sensors, applications and devices are used by a company to identify security issues for IIOT. Visibility of work is overseen by a firm to gather several types of information related to work. Every company always tries to enhance troubleshooting and maintenance capabilities. Regulatory compliance is controlled by an organisation to understand issues of IIOT. Operational efficiency improves by these security issues for IIOT process. Quality assurance and artificial intelligence are controlled with help of these security issues. Digital transformation helps a company to mitigate those issues for IIOT. Lack of visibility, security integration and poor testing related issues are faced by a firm. Centralised connectivity helps an organisation to connect all networks in an organised way. This centralised connectivity plays an essential role to control performance. Secondary network system is managed by a company to mitigate security issues for IIOT. Several types of modern IoT devices are used for mitigating security issues. Keyword : Security issues, IIOT, IOT, centralised connectivity.

show abstract

“…Randhir Kumar et al [17] put forth a fog computing solution to detect DDoS attacks in blockchain-enabled IoT networks, achieving efficient detection compared to traditional methods. Mohanad Sarhan et al [18] proposed a hierarchical blockchain-based federated learning framework for IoT intrusion detection, ensuring enhanced security while maintaining data integrity.…”

mentioning

confidence: 99%

BlockFog: A Blockchain-based Framework for Intrusion Defense in IOT Fog Computing

VG,

Babu,

Pydala

2024

SCPE

View full text Add to dashboard Cite

In the rapidly evolving domain of the Internet of Things (IoT) and fog computing, maintaining security, scalability, and efficient operation poses significant challenges. Addressing these issues, this study introduces "BlockFog," a novel blockchain-based framework designed to bolster intrusion defense in IoT fog computing environments. The core objective of BlockFog is to counteract the vulnerabilities inherent in decentralized IoT ecosystems by leveraging blockchain technology for enhanced security and transparency. The framework's innovative design integrates crucial components such as Device Onboarding & Identity Management, Data Integrity & Logging, Smart Contract-Driven Intrusion Detection, Automated Blockchain Responses, Secure Peer-to-Peer Communication, and a Lightweight Consensus Mechanism. These elements work collectively to ensure the security and functionality of IoT devices within the fog computing paradigm. BlockFog stands out for its meticulous approach to handling high transaction volumes with off-chain computations and layer-2 solutions, ensuring data integrity and facilitating seamless audit processes. The framework's resilience is further demonstrated through its robust response to evolving cyber threats, incorporating Over-the-Air (OTA) updates and advanced data protection mechanisms like zero-knowledge proofs. A comparative analysis highlights BlockFog's superior performance against existing models. The results reveal BlockFog's lower latency rates in normal, high traffic, and attack scenarios, its higher throughput efficiency, and its more effective resource utilization in terms of CPU, memory, and bandwidth usage. Moreover, BlockFog exhibits an enhanced ability to detect and respond to malicious activities, including DDoS attacks, with significantly higher accuracy than its counterparts. These findings underscore BlockFog's potential in redefining security and operational paradigms in IoT fog computing, making it a robust, agile, and transparent framework suitable for the current digital landscape.

show abstract

HBFL: A hierarchical blockchain-based federated learning framework for collaborative IoT intrusion detection

Cited by 44 publications

References 22 publications

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

A Study into the Security Issues and Countermeasures for the Industrial Internet of Things (IIOT)

BlockFog: A Blockchain-based Framework for Intrusion Defense in IOT Fog Computing

Contact Info

Product

Resources

About