Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity
Abstract In the digital age, privacy preservation is of paramount importance while processing health-related sensitive information. This paper explores the integration of Federated Learning (FL) and Differential Privacy (DP) for breast cancer detection, leveraging FL’s decentralized architecture to...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-95858-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850146374110150656 |
|---|---|
| author | Shubhi Shukla Suraksha Rajkumar Aditi Sinha Mohamed Esha Konguvel Elango Vidhya Sampath |
| author_facet | Shubhi Shukla Suraksha Rajkumar Aditi Sinha Mohamed Esha Konguvel Elango Vidhya Sampath |
| author_sort | Shubhi Shukla |
| collection | DOAJ |
| description | Abstract In the digital age, privacy preservation is of paramount importance while processing health-related sensitive information. This paper explores the integration of Federated Learning (FL) and Differential Privacy (DP) for breast cancer detection, leveraging FL’s decentralized architecture to enable collaborative model training across healthcare organizations without exposing raw patient data. To enhance privacy, DP injects statistical noise into the updates made by the model. This mitigates adversarial attacks and prevents data leakage. The proposed work uses the Breast Cancer Wisconsin Diagnostic dataset to address critical challenges such as data heterogeneity, privacy-accuracy trade-offs, and computational overhead. From the experimental results, FL combined with DP achieves 96.1% accuracy with a privacy budget of ε = 1.9, ensuring strong privacy preservation with minimal performance trade-offs. In comparison, the traditional non-FL model achieved 96.0% accuracy, but at the cost of requiring centralized data storage, which poses significant privacy risks. These findings validate the feasibility of privacy-preserving artificial intelligence models in real-world clinical applications, effectively balancing data protection with reliable medical predictions. |
| format | Article |
| id | doaj-art-b496afb32c2048338fb04db39dbef4fe |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b496afb32c2048338fb04db39dbef4fe2025-08-20T02:27:52ZengNature PortfolioScientific Reports2045-23222025-04-0115113310.1038/s41598-025-95858-2Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrityShubhi Shukla0Suraksha Rajkumar1Aditi Sinha2Mohamed Esha3Konguvel Elango4Vidhya Sampath5School of Electrical Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, Vellore Institute of TechnologySchool of Mechanical Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, Vellore Institute of TechnologyAbstract In the digital age, privacy preservation is of paramount importance while processing health-related sensitive information. This paper explores the integration of Federated Learning (FL) and Differential Privacy (DP) for breast cancer detection, leveraging FL’s decentralized architecture to enable collaborative model training across healthcare organizations without exposing raw patient data. To enhance privacy, DP injects statistical noise into the updates made by the model. This mitigates adversarial attacks and prevents data leakage. The proposed work uses the Breast Cancer Wisconsin Diagnostic dataset to address critical challenges such as data heterogeneity, privacy-accuracy trade-offs, and computational overhead. From the experimental results, FL combined with DP achieves 96.1% accuracy with a privacy budget of ε = 1.9, ensuring strong privacy preservation with minimal performance trade-offs. In comparison, the traditional non-FL model achieved 96.0% accuracy, but at the cost of requiring centralized data storage, which poses significant privacy risks. These findings validate the feasibility of privacy-preserving artificial intelligence models in real-world clinical applications, effectively balancing data protection with reliable medical predictions.https://doi.org/10.1038/s41598-025-95858-2Federated learningData securityPrivacy preservationHealthcareDecentralized machine learningDifferential privacy |
| spellingShingle | Shubhi Shukla Suraksha Rajkumar Aditi Sinha Mohamed Esha Konguvel Elango Vidhya Sampath Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity Scientific Reports Federated learning Data security Privacy preservation Healthcare Decentralized machine learning Differential privacy |
| title | Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity |
| title_full | Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity |
| title_fullStr | Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity |
| title_full_unstemmed | Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity |
| title_short | Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity |
| title_sort | federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity |
| topic | Federated learning Data security Privacy preservation Healthcare Decentralized machine learning Differential privacy |
| url | https://doi.org/10.1038/s41598-025-95858-2 |
| work_keys_str_mv | AT shubhishukla federatedlearningwithdifferentialprivacyforbreastcancerdiagnosisenablingsecuredatasharingandmodelintegrity AT suraksharajkumar federatedlearningwithdifferentialprivacyforbreastcancerdiagnosisenablingsecuredatasharingandmodelintegrity AT aditisinha federatedlearningwithdifferentialprivacyforbreastcancerdiagnosisenablingsecuredatasharingandmodelintegrity AT mohamedesha federatedlearningwithdifferentialprivacyforbreastcancerdiagnosisenablingsecuredatasharingandmodelintegrity AT konguvelelango federatedlearningwithdifferentialprivacyforbreastcancerdiagnosisenablingsecuredatasharingandmodelintegrity AT vidhyasampath federatedlearningwithdifferentialprivacyforbreastcancerdiagnosisenablingsecuredatasharingandmodelintegrity |