Towards Privacy-Preserving Medical Imaging: Federated Learning with Differential Privacy and Secure Aggregation Using a Modified ResNet Architecture

Mohamad Haj Fares, Ahmed Mohamed Saad Emam Saad

Keywords: Federated Learning, Differential Privacy, Medical Imaging, Secure Multi-Party Computation (SMPC), ResNet Architecture, Privacy-Preserving AI

TL;DR: Privacy-preserving federated learning framework combining differential privacy, secure aggregation, and a modified ResNet architecture achieves state-of-the-art accuracy on BloodMNIST while maintaining robust privacy guarantees.

Abstract: With increasing concerns over privacy in healthcare, especially for sensitive medical data, this research introduces a federated learning framework that combines local differential privacy and secure aggregation using Secure Multi-Party Computation for medical image classification. Further, we propose DPResNet, a modified ResNet architecture optimized for differential privacy. Leveraging the BloodMNIST benchmark dataset, we simulate a realistic data-sharing environment across different hospitals, addressing the distinct privacy challenges posed by federated healthcare data. Experimental results indicate that our privacy-preserving federated model achieves accuracy levels close to non-private models, surpassing traditional approaches while maintaining strict data confidentiality. By enhancing the privacy, efficiency, and reliability of healthcare data management, our approach offers substantial benefits to patients, healthcare providers, and the broader healthcare ecosystem.

Submission Number: 24