DeepFed: Federated Learning with Differential Privacy for Secure Healthcare Data Analysis
Keywords:
Federated learning, differential privacy, secure healthcare, medical imaging, privacy-preservingAbstract
To ensure secure, privacy-preserving healthcare data analysis an advanced federated learning (FL) Environment is integrated with differential privacy (DP) which is known as DeepFed. As the proposed framework facilitates collaborative model training across multiple healthcare institutions without exposing sensitive patient data and addressing critical challenges in privacy, security, and regulatory compliance. The objective of this paper is to utilise the decentralised deep neural networks for DeepFed which enhances diagnostic accuracy for medical imaging and electronic health record (EHR) datasets while mitigating the risk of data breaches.
Downloads
References
Y. Liu, K. Xu, C. Sun, and H. Li, “Privacy-preserving federated learning for healthcare: Challenges and solutions,” IEEE Transactions on Emerging Topics in Computing, vol. 10, no. 3, pp. 1403–1415, Sep. 2022.
B. McMahan, D. Ramage, K. Talwar, and L. Zhang, “Learning differentially private language models without losing accuracy,” in Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021.
L. Truex, L. Liu, K. Yuan, and W. Zhai, “Towards demystifying membership inference attacks,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 5, pp. 2191–2203, May 2022.
T. Li, A. S. Sahu, M. Zaheer, and V. Smith, “Federated learning: Challenges, methods, and future directions,” IEEE Signal Processing Magazine, vol. 39, no. 3, pp. 50–60, May 2022.
S. Rieke, J. Hancox, and J. McConnell, “Federated learning for medical imaging with privacy-preserving technologies,” Nature Machine Intelligence, vol. 3, no. 6, pp. 492–506, Jun. 2021.
P. Kairouz, H. McMahan, and B. Avent, “Advances and open problems in federated learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1, pp. 1–210, Jan. 2021.
A. Abadi, M. Goodfellow, and I. McSherry, “Deep learning with differential privacy,” in Proceedings of the 23rd ACM SIGSAC Conference on Computer and Communications Security (CCS), Vienna, Austria, 2016, pp. 308–318.
M. Nasr, R. Shokri, and A. Houmansadr, “Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,” in Proceedings of the 40th IEEE Symposium on Security and Privacy (S&P), San Francisco, CA, USA, 2019, pp. 739–753.
Z. Xu, S. Huo, and J. Zhou, “Efficient and privacy-preserving federated learning for medical diagnosis,” IEEE Internet of Things Journal, vol. 8, no. 4, pp. 2384–2397, Feb. 2021.
N. Papernot, M. Abadi, and U. Erlingsson, “Semi-supervised knowledge transfer for deep learning from private training data,” in Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France, 2017.
T. Salamati, M. Seyedzadeh, and R. Bahar, “Hardware-aware privacy-preserving federated learning for medical AI applications,” IEEE Transactions on Medical Imaging, vol. 41, no. 3, pp. 671–684, Mar. 2022.
X. Zhang, J. Wang, and L. Zhang, “Federated learning with differential privacy: Algorithm design and performance analysis,” IEEE Transactions on Information Forensics and Security, vol. 17, pp. 1482–1496, 2022.
J. Zhao, W. Liu, and Y. Gong, “Privacy-preserving federated learning in medical applications,” in Proceedings of the IEEE International Conference on Artificial Intelligence and Security (ICAIS), 2022, pp. 123–134.
K. Bonawitz, H. Eichner, and L. Roy, “Practical secure aggregation for privacy-preserving machine learning,” in Proceedings of the 25th ACM SIGSAC Conference on Computer and Communications Security (CCS), Toronto, Canada, 2017, pp. 1175–1191.
Y. Zhou, Y. Sun, and J. Zhang, “Adversarial attacks and defenses in federated learning,” IEEE Internet of Things Journal, vol. 9, no. 3, pp. 3456–3467, Feb. 2022.
C. Dwork, “Differential privacy: A survey of results,” in Proceedings of the 33rd International Conference on Automata, Languages and Programming (ICALP), Venice, Italy, 2006, pp. 1–12.
M. Mohri, G. Sivek, and A. Suresh, “Agnostic federated learning,” in Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019, pp. 4615–4625.
J. Huang, Y. Ma, and Z. Wang, “Scalable and privacy-preserving federated learning with differential privacy,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 2, pp. 2567–2580, 2023.
L. Liu, T. Chen, and H. Yang, “Federated learning meets blockchain: Opportunities and challenges,” IEEE Internet of Things Journal, vol. 8, no. 6, pp. 4250–4265, Mar. 2021.
A. Phong, T. Aono, and K. Hayashi, “Privacy-preserving deep learning via additively homomorphic encryption,” IEEE Transactions on Information Forensics and Security, vol. 14, no. 11, pp. 2933–2945, Nov. 2019.
