A Cutting-Edge Security Solution System for Smart Home by Applying the Intelligent AI And BC Framework to Secure Data

Abstract

Revolutionary technologies like blockchain and artificial intelligence (AI) have come together due to the fast Internet of Things (IoT) growth. Thanks to these technologies coming together, complex infrastructures like "smart homes," "smart cities," and "smart industries" have become possible to build. While IoT gadgets may provide excellent connection and convenience, they often use insecure conventional network interfaces. These older communication protocols and interfaces may be vulnerable if they aren't securely upgraded and protected. This research has developed a strong framework that utilizes the AI along with blockchain technology capabilities to work with the security concerns related to smart home systems (SHS). To start, the research used an isolation forest (IF) algorithm with random segmentation, anomaly score computation, route length, as well as thresholding phases to get rid of the weird data in a normal dataset for SHS. To further categorize the data as either attack or non-attack, the dataset is then used to train classification algorithms including Catboost, K-nearest neighbors (KNN), support vector machines (SVM), and linear discriminate analysis (LDA). When protecting sensitive information from data manipulation assaults, it is also stored in an interplanetary file system (IPFS). In order to save non-attack data safely, IPFS functions as an onsite storage system; the generated hash is then sent to the immutable register of the blockchain. Different performance metrics were used to assess the proposed framework.