Implementation and Validation of a Digital Privacy Framework for Crowdsourced IoT Data Processing

Abstract

The proposed privacy-preserving crowdsourcing framework integrates IoT-based anomaly detection with differential privacy, homomorphic encryption, and federated learning. The framework protects data gathering, anonymization, and processing while ensuring accurate outcomes. The framework is built using Flask and Isolation Forest, which ensures the balance between utility and privacy while providing security for crowdsourced IoT applications for real-world deployment.