By: Soo Nee Kee1,2
1Universiti Malaya, Kuala Lumpur, Malaysia.
2International Center for AI and Cyber Security Research and Innovations, Asia University, Taiwan Email: nee.kee2001.nks@gmail.com
Abstract
The integration of blockchain technology with Internet of Things (IoT) is widely used in many sectors to improve performance and efficiency. The paper proposes a blockchain-based system to enhance security, transparency, traceability and efficiency in agricultural practices. The system consists of five layers: sensor layer, edge layer, blockchain layer, application layer and irrigation layer. Each layer integrates and communicates well to perform anomalies detection, data encryption and data processing to gain better crop yields. Federated learning is implemented to improve the security of the system. It conducts anomalies and vulnerabilities detection. AES-256 and ABE are used for secure data transmission. The application layer provides interfaces for different user groups, enhancing usability and decision-making capabilities. The application layer customizes interfaces for various user groups, improving usability and decision-making capabilities.
Keywords: Blockchain, Authentication, Security, IoT, Smart Agriculture, Attribute-based Encryption
Introduction
Blockchain has been used in many sectors in order to improve security, transparency, traceability and efficiency. Blockchain can be used in the agriculture sector as well to help build smart agriculture systems. In recent years, natural disasters have occurred frequently, resulting in poor crop yields. Therefore, integration of blockchain and IoT networks is being developed to monitor the crops and environmental conditions and prevent significant losses. The system can provide in real-time environmental conditions monitoring, automated responses to environmental changes, and enhance immutability and traceability.
Proposed Framework
This paper proposed a system architecture that integrates IoT networks with blockchain to improve the security of the system and efficiency of agricultural practices. There are five layers in this system architecture: sensor layer, edge layer, blockchain layer, application layer, irrigation layer. [1] The sensor layer consists of various sensors, such as temperature sensors, air humidity sensors, soil pH sensors, light intensity sensors and carbon dioxide sensors. They can monitor and collect the data for future analysis. Besides, Federated learning can be implemented in this layer to detect the anomalies locally. Federated learning is a type of machine learning that trains models on each sensor and the updated models will be sent to a central server to aggregate updates and enhance model’s accuracy. The updated global model is distributed to each sensor to perform real-time detection. [2] It ensures privacy and security as the sensitive data is not transmitted and allows for real-time responses to anomalies since the data is not being transferred. If an anomaly is detected, it will notify the irrigation layer to response. For example, the irrigation layer will lower the temperature if the temperature rises above 30 degrees Celsius. The safe data will be encrypted by using AES-256 before it is transferred to the edge gateway.
Edge gateway will collect the data from various sensors. The data will then be transferred to the edge server for data processing and encryption. The data is being filtered, aggregated and analyzed to reduce the amount of data sent to the blockchain in order to minimize the latency and bandwidth usage. After that, the processed data will be encrypted by using Attributed-based encryption (ABE). ABE ensures the only authorized users can access the data. Since not all data is open to the public and different groups of users can access different data, ABE is suitable in this case to provide fine-grained access over encrypted data, allowing authorized users that meet the access policies to access the data. [3] For example, data owner can set the data “amount and quality fertilizers used” only viewable for the buyers while the trading transaction details are internal use only, between the farmers and the firms. [4] The encrypted data is sent to blockchain to store. Due to the immutable and traceable features of blockchain, tampering data without permission can be avoided. Application layer includes various apps, websites and dashboards designed for different groups of users. For example, the dashboard is used for the firms to monitor the yields and trading transaction details. The website is for the buyers to know more about the products and services to purchase it.
Conclusion
In conclusion, the integration of blockchain with IoT devices, the implementation of federated learning and encryption (AES-256 and ABE) play an important role in improving the security of a smart agriculture system. Blockchain can ensure the immutability and traceability of data, to prevent any malicious changes on the data. Federated learning can help in detecting anomalies and give responses in real-time since all data are trained locally. AES-256 encryption can ensure the secure data transmission across the network from sensor layer to edge layer while ABE consists of a set of access policies to allow users who fulfill the policies to gain access on the data, further strengthening the security and privacy of the system.
Reference
- “Exploring the integration of edge computing and blockchain IoT: Principles, architectures, security, and applications – ScienceDirect.” Accessed: Oct. 04, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1084804524000614
- I. Priyadarshini, “Anomaly Detection of IoT Cyberattacks in Smart Cities Using Federated Learning and Split Learning,” Big Data Cogn. Comput., vol. 8, no. 3, Art. no. 3, Feb. 2024, doi: 10.3390/bdcc8030021.
- “A Secure Data Sharing Platform Using Blockchain and Interplanetary File System.” Accessed: Oct. 04, 2024. [Online]. Available: https://www.mdpi.com/2071-1050/11/24/7054
- “Smart Contract-Based Blockchain-Envisioned Authentication Scheme for Smart Farming | IEEE Journals & Magazine | IEEE Xplore.” Accessed: Oct. 06, 2024. [Online]. Available: https://ieeexplore.ieee.org/document/9319194
- Chaudhary, P., Gupta, B. B., & Singh, A. K. (2022). XSS Armor: Constructing XSS defensive framework for preserving big data privacy in internet-of-things (IoT) networks. Journal of Circuits, Systems and Computers, 31(13), 2250222.
- Sedik, A., Maleh, Y., El Banby, G. M., Khalaf, A. A., Abd El-Samie, F. E., Gupta, B. B., … & Abd El-Latif, A. A. (2022). AI-enabled digital forgery analysis and crucial interactions monitoring in smart communities. Technological Forecasting and Social Change, 177, 121555.
- Mourelle, L. M. (2022). Robotics and AI for Cybersecurity and Critical Infrastructure in Smart Cities. N. Nedjah, A. A. Abd El-Latif, & B. B. Gupta (Eds.). Springer.
Cite As
Kee S.N. (2024) Blockchain-Based Authentication and Security for IoT in Smart Agriculture, Insights2Techinfo, pp.1