Secure Integer Comparison Protocol For ML-based Disease Diagnosis In MHN With Energy Efficient Edge Computing

The benefits that MHN offers to healthcare services are not fully garnered due to concerns on privacy and security of sensitive medical data. Severe constraints on battery capacity and computing resources at the edge devices of MHN impose restrictions in deploying strong secure systems. Medical data need to be stored, communicated, and processed securely in real-time. Homomorphic encryption help to perform linear operations securely on the encrypted data. More complicated operations like ML-based disease diagnosis require nonlinear operations such as integer comparison. Hence a secure multiparty computation over homomorphically encrypted data is required for secure integer comparison. However, comparison protocols available in the literature use energy-hungry public-key cryptosystems. This article presents the design of an energy-efficient additively homomorphic modified Rivest scheme (AHMRS) to support secure integer comparison protocol (SICP-AHMRS), which facilitates fast and energy-efficient ML-based disease diagnosis. The proposed SICP-AHMRS guarantees the privacy of the data being compared. The experiments using the Raspberry Pi 3B+ board show that the energy consumption, processing delay, and bandwidth efficiency of the proposed SICP-AHMRS are much better than those of the existing schemes.