The widespread adoption of Internet of Things (IoT) devices has opened new possibilities for data-driven decision making while simultaneously raising serious concerns about the protection of sensitive personal information. This paper presents an integrated privacy-preserving data aggregation framework that strategically combines homomorphic encryption, secure multi-party computation, and differential privacy mechanisms. We design a hierarchical three-tier protocol architecture in which IoT devices encrypt their measurements using Paillier homomorphic encryption, edge nodes carry out secure aggregation through distributed computation, and cloud servers inject calibrated differential privacy noise prior to threshold-based decryption. The framework reduces reliance on trusted third parties through Shamir secret sharing while striving to maintain computational efficiency appropriate for resource-constrained devices. Experimental evaluation involving 1000 simulated IoT devices across 30 independent trials demonstrates that the protocol completes aggregation in 3.82 ± 0.35 s (mean ± standard deviation) with 2.8% ± 0.6% relative error under moderate privacy budgets (ε = 1.0, 95% CI: 2.4%, 3.2%). Security analysis under the semi-honest adversary model indicates that the protocol satisfies semantic security assumptions and ε-differential privacy guarantees. These results suggest that meaningful privacy protection can be achieved while preserving practical utility, offering a potential solution for privacy-sensitive IoT deployments in smart cities, healthcare monitoring, and industrial applications, although certain limitations regarding scalability and adversary models require further investigation.
Qin et al. (2026) studied this question.