A service-oriented microservice framework for differential privacy-based protection in industrial IoT smart applications

Abstract

The rapid advancement of key technologies such as Artificial Intelligence (AI), the Internet of Things (IoT), and edge-cloud computing has significantly accelerated the transformation toward smart industries across various domains, including finance, manufacturing, and healthcare. Edge and cloud computing offer low-cost, scalable, and on-demand computational resources, enabling service providers to deliver intelligent data analytics and real-time insights to end-users. However, despite their potential, the practical adoption of these technologies faces critical challenges, particularly concerning data privacy and security. AI models, especially in distributed environments, may inadvertently retain and leak sensitive training data, exposing users to privacy risks in the event of malicious attacks. To address these challenges, this study proposes a privacy-preserving, service-oriented microservice architecture tailored for intelligent Industrial IoT (IIoT) applications. The architecture integrates Differential Privacy (DP) mechanisms into the machine learning pipeline to safeguard sensitive information. It supports both centralised and distributed deployments, promoting flexible, scalable, and secure analytics. We developed and evaluated differentially private models, including Radial Basis Function Networks (RBFNs), across a range of privacy budgets (ɛ), using both real-world and synthetic IoT datasets. Experimental evaluations using RBFNs demonstrate that the framework maintains high predictive accuracy (up to 96.72%) with acceptable privacy guarantees for budgets [Formula: see text]. Furthermore, the microservice-based deployment achieves an average latency reduction of 28.4% compared to monolithic baselines. These results confirm the effectiveness and practicality of the proposed architecture in delivering privacy-preserving, efficient, and scalable intelligence for IIoT environments. Additionally, the microservice-based design enhanced computational efficiency and reduced latency through dynamic service orchestration. This research demonstrates the feasibility of deploying robust, privacy-conscious AI services in IIoT environments, paving the way for secure, intelligent, and scalable industrial systems.

Keywords: Differential privacy; Distributed machine learning; Edge-cloud computing; Health care sector; Industrial Internet of Things (IIoT); Microservices architecture; Privacy; Radial basis function network (RBFN).

Fig. 1

Conventional methodology for the training and deployment of machine learning models within a cloud infrastructure (the diagram was created using the Draw.io tool, available at https://www.drawio.com/).

Fig. 2

RBFN architecture consisting of input, hidden (Gaussian), and output layers.

Fig. 3

System model for training and deploying a differentially-private RBFN via microservices.

Fig. 4

End-to-end privacy-preserving workflow for IIoT using edge-cloud microservices.

Fig. 5

Using differential privacy and microservices, a distributed radial basis function network architecture.

Fig. 6

Private edge server.

Algorithm 1

Randomised training microservice (RTMS) configuration

Algorithm 2

DAMS: Data Aggregation Microservice

Fig. 7

Accuracy comparison of centralised baseline model centre selection methods.

Fig. 8

Centralised RBFN model accuracy under varying privacy budgets.

Fig. 9

Accuracy across datasets under distributed differential privacy.

Fig. 10

Bar plot of accuracy vs. privacy budget for different datasets.

Fig. 11

Accuracy trends across budgets and datasets.

Fig. 12

Execution time comparison: monolithic vs. microservice architecture.