The Internet of Things (IoT) describes a system where interconnected physical objects are connected online. As the collection and sharing of vast amounts of personal data grow, so do concerns over user privacy within IoT environments. While IoT devices offer significant advantages in terms of productivity, accuracy, and financial benefits by minimizing human intervention and providing exceptional flexibility and convenience, they also face challenges related to communication overhead, security, and privacy. To address these issues, a novel Internet of Things-based Cloud Information Security Preservation (IoT-CISP) has been proposed. This approach enhances the model’s effectiveness and ensures security by first separating sensitive data from nonsensitive data using an SVM classifier, and then employing this data for partial decryption and analysis. Sensitive data is protected through Okamoto-Uchiyama encryption, ensuring that data storage, analysis, and sharing are conducted securely to maintain the system’s safety and privacy. The effectiveness of this novel method was assessed against existing methodologies using parameters like precision, accuracy, F1 score, and recall, revealing its superior security and efficiency compared to other schemes. Results demonstrate that the IoTCISP approach offers encryption times that are 31.24%, 23.12%, and 33.03% shorter than those of the CP-ABE, GDBR, and HP-CPABE algorithms, respectively.