Leveraging TenSEAL

Abstract

In our interconnected world, the use of Internet of Things (IoT) devices generates vast amounts of sensitive data. To secure this data while extracting insights, privacy-preserving machine learning (PPML) tools like Fully Homomorphic Encryption (FHE) are crucial. This study compares two FHE schemes, BFV and CKKS, for protecting IoT data during PPML analysis. Logistic regression models are implemented on encrypted datasets using the TenSEAL library, and the accuracy and efficiency are compared with unencrypted data. The study focuses on privacy preservation, computational overhead, and model accuracy. Using the capabilities of TenSEAL, the study finds that both BFV and CKKS effectively preserve IoT data privacy during ML tasks. BFV demonstrates superior computational efficiency, enabling faster analysis and training, while CKKS achieves higher accuracy in predicting IoT data. This study aids researchers in selecting the most suitable homomorphic encryption scheme for their needs.