Privacy-Preserving Data Aggregation in Smart Cities: Secure and Efficient Techniques for Urban Data Management

The fast growth of smart cities has resulted in an exponential rise in data gathering from different IoT devices and sensors. Although the data is essential for urban planning and smart services, maintaining privacy while aggregating data is a major challenge. Conventional aggregation techniques tend to violate user privacy, and hence there is a need to create secure and efficient privacy-preserving methods. This work investigates cutting-edge cryptographic techniques, differential privacy mechanisms, and federated learning methods to support secure data aggregation with data utility preservation. We introduce a new framework that increases security, decreases computational overhead, and supports scalability for large-scale smart city deployments. Experimental outcomes show the proposed model's capability to balance efficiency and privacy.