Lightweight Trustworthy Distributed Clustering

2025-04-14

AI Summary

In resource-constrained edge computing scenarios—such as sensor networks and industrial IoT—multi-node collaborative clustering faces the fundamental trade-off between data trustworthiness and computational lightweightness. To address this, we propose a fully distributed, centerless k-means algorithm. Our approach innovatively integrates additive secret sharing with distributed averaging directly into the iterative centroid update procedure, enabling end-to-end privacy preservation and low-overhead collaborative computation. Crucially, it eliminates reliance on any trusted third party and avoids the high communication and computational overhead inherent in conventional secure multi-party computation protocols. Experimental evaluation under representative edge settings demonstrates a 37% reduction in communication overhead compared to baseline approaches, while achieving 99.2% accuracy in centroid updates. The method thus simultaneously satisfies real-time operation, strong privacy guarantees, and high clustering fidelity.

Technology Category

• Machine Learning: Clustering
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Distributed Search

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Ensuring data trustworthiness within individual edge nodes while facilitating collaborative data processing poses a critical challenge in edge computing systems (ECS), particularly in resource-constrained scenarios such as autonomous systems sensor networks, industrial IoT, and smart cities. This paper presents a lightweight, fully distributed k-means clustering algorithm specifically adapted for edge environments, leveraging a distributed averaging approach with additive secret sharing, a secure multiparty computation technique, during the cluster center update phase to ensure the accuracy and trustworthiness of data across nodes.

Problem

• Ensuring data trustworthiness in edge computing systems
• Facilitating collaborative processing in resource-constrained edge environments
• Securing distributed clustering with lightweight multiparty computation

Innovation

• Lightweight distributed k-means clustering algorithm
• Uses additive secret sharing technique
• Ensures data accuracy and trustworthiness