Privacy Armor for IoT: A Fusion Framework of Blockchain and LSTM for Data Security
Jun Hu, Gang Du, Qian Wang, Xin Jin · 2023
The rapid development of the Internet of Things (IoT) has led to an exponential increase in the number of connected devices and sensors, resulting in the generation of a massive volume of data. However, ensuring the security of this data has become a critical concern. This paper proposes an IoT data security framework that utilizes both blockchain and LSTM. The framework adopts a distributed cloud-fog-IoT architecture, utilizing IPFS for off-chain storage. This combination guarantees data immutability, traceability, and verifiability. To ensure node trustworthiness and data privacy, the framework incorporates a privacy protection module based on blockchain and principal component analysis. Moreover, a LSTM-based security module is introduced to detect anomalous behavior in heterogeneous networks. Experimental results indicate that this framework not only provides robust security measures but also significantly reduces the operational costs associated with blockchain technology,