T5, 14/11/2024 - 13:55
Thông tin bài báo:
- Tên bài báo: Enhancing Security for Smart Ehealthcare System based on Federated Learning and Homomorphic Encryption
- Sinh viên thực hiện:
+ Nguyễn Khánh Duy – MMCL 2020 – Tác giả chính
+ Huỳnh Phú Lợi – MMCL 2020 – Đồng tác giả
+ Phan Trung Kiên – MMCL 2020 – Đồng tác giả
- Giảng viên hướng dẫn: PGS. TS. Lê Trung Quân, ThS. Nguyễn Khánh Thuật
Tóm tắt bài báo:
Medical records are one of the most sensitive types of data, so when applying machine learning models, it is necessary to ensure data privacy. In recent years, machine learning and pre-trained models have been developing rapidly, and medical data security when using those models is gaining strong appeal with researchers. This study proposes a federated learning model integrated with homomorphic encryption to enhance security and privacy while training machine learning models on medical datasets. Additionally, we conducted experiments with federated learning models using different data distribution ratios to evaluate the robustness of this approach. The results show that the CNN, ResNet50, ResNet152, and DenseNet169 models integrated with federated learning on the LIDC-IDRI dataset have comparable accuracy to centralized machine learning. Moreover, the federated learning model integrated with Homomorphic Encryption on the ResNet50 model showed a 4% increase in training time and a 36% increase in model size compared to federated learning without encryption.
Thông tin Hội nghị:
The International Conference on Advanced COMPuting and Analytics (ACOMPA) is an annual international forum for academics, engineers, practitioners and research students to exchange concepts, techniques, methods, and state-of-the-art applications for advanced computing & analytics. Initially formed as a scientific venue for high-performance computing & advanced applications, the conference kept expanding and had the pedigree of attracting international and Vietnamese participants who are all interested in advanced topics of computer science & engineering. The first occurrence of ACOMPA dates back to as early as 2007.
Advanced computing was the main themes of ACOMPA for more than dozen years, making it a popular scientific event for high performance, scientific computing and system design in the region. Overtime, the conference’s body has evolved into a refreshingly expanded community of scholars, research students and practitioners whose interests include not only computing systems but also advanced analytics and its emerging enablers (data science, deep learning, process automation, etc.). On one hand, there has been growing attention in harvesting advanced computing systems in use today to make advanced analytics technically possible. On the other hand, with the rise of machine learning and data science, we expect to revisit our research questions and practical problems lingering in advanced computing that might have been inadequately addressed. In the year 2022, we acknowledged such a transitional change and began to use ACOMPA as our conference abbreviation
- Link hội nghị:
Mọi thông tin chi tiết xem tại:
Đông Xanh - Cộng tác viên truyền thông Trường bet365 betting
