Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things
The rapid increase in Internet of Things (IoT) applications has exposed critical security vulnerabilities, particularly concerning user privacy and identity forgery. To address these concerns, Blockchain technology offers a promising solution by providing strong security and ensuring data integrity...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2025.2459461 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849689347485335552 |
|---|---|
| author | Arunkumar Muniswamy R. Rathi |
| author_facet | Arunkumar Muniswamy R. Rathi |
| author_sort | Arunkumar Muniswamy |
| collection | DOAJ |
| description | The rapid increase in Internet of Things (IoT) applications has exposed critical security vulnerabilities, particularly concerning user privacy and identity forgery. To address these concerns, Blockchain technology offers a promising solution by providing strong security and ensuring data integrity through its transparent ledger system. By leveraging blockchain, IoT systems can enhance their security protocols, making it more difficult for attackers to exploit vulnerabilities and access sensitive data. We proposed Attribute-Based Access Control (ABAC) integrated with trust-based delegated consensus blockchain (TDCB) technology. The ABAC scheme employs Fully Homomorphic Encryption (FHE) processes to encrypt attributes and access regulations, enabling analytical operations directly on encrypted data. Dueling Double Deep Q-Networks with Prioritized Experience Replay (D3P) with Deep Reinforcement Learning (DRL) collaborate with Multiple blockchain nodes to decode the ABAC system’s data and optimize the performances of the blockchain. Our proposed scheme ABAC-TDBC-D3P enhances throughput and security and reduces total computing costs. The simulation results demonstrate that the suggested ABAC-TDCB-D3P scheme has a percentage of 86% for Collusive Rumour Attack (CRA) and 91% for Naive Malicious Attack (NMA). Significant improvements in blockchain security, particularly in mitigating the impact of malicious nodes, were compared to previous schemes. |
| format | Article |
| id | doaj-art-18a774a8a66842c5a06351d5eeb89930 |
| institution | DOAJ |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-18a774a8a66842c5a06351d5eeb899302025-08-20T03:21:40ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452025-12-0139110.1080/08839514.2025.2459461Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of ThingsArunkumar Muniswamy0R. Rathi1School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, IndiaSchool of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, IndiaThe rapid increase in Internet of Things (IoT) applications has exposed critical security vulnerabilities, particularly concerning user privacy and identity forgery. To address these concerns, Blockchain technology offers a promising solution by providing strong security and ensuring data integrity through its transparent ledger system. By leveraging blockchain, IoT systems can enhance their security protocols, making it more difficult for attackers to exploit vulnerabilities and access sensitive data. We proposed Attribute-Based Access Control (ABAC) integrated with trust-based delegated consensus blockchain (TDCB) technology. The ABAC scheme employs Fully Homomorphic Encryption (FHE) processes to encrypt attributes and access regulations, enabling analytical operations directly on encrypted data. Dueling Double Deep Q-Networks with Prioritized Experience Replay (D3P) with Deep Reinforcement Learning (DRL) collaborate with Multiple blockchain nodes to decode the ABAC system’s data and optimize the performances of the blockchain. Our proposed scheme ABAC-TDBC-D3P enhances throughput and security and reduces total computing costs. The simulation results demonstrate that the suggested ABAC-TDCB-D3P scheme has a percentage of 86% for Collusive Rumour Attack (CRA) and 91% for Naive Malicious Attack (NMA). Significant improvements in blockchain security, particularly in mitigating the impact of malicious nodes, were compared to previous schemes.https://www.tandfonline.com/doi/10.1080/08839514.2025.2459461 |
| spellingShingle | Arunkumar Muniswamy R. Rathi Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things Applied Artificial Intelligence |
| title | Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things |
| title_full | Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things |
| title_fullStr | Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things |
| title_full_unstemmed | Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things |
| title_short | Trust-Based Consensus and ABAC for Blockchain Using Deep Learning to Secure Internet of Things |
| title_sort | trust based consensus and abac for blockchain using deep learning to secure internet of things |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2025.2459461 |
| work_keys_str_mv | AT arunkumarmuniswamy trustbasedconsensusandabacforblockchainusingdeeplearningtosecureinternetofthings AT rrathi trustbasedconsensusandabacforblockchainusingdeeplearningtosecureinternetofthings |