A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing
Protecting sensitive health information and promoting clinical research depend on medical data security. This paper suggests an innovative framework that integrates healthcare engineering, chaotic encryption, and artificial intelligence (AI) to address the privacy issue of medical data. A novel semi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123024021297 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527950308016128 |
|---|---|
| author | Animesh Roy Deva Raj Mahanta Lipi B. Mahanta |
| author_facet | Animesh Roy Deva Raj Mahanta Lipi B. Mahanta |
| author_sort | Animesh Roy |
| collection | DOAJ |
| description | Protecting sensitive health information and promoting clinical research depend on medical data security. This paper suggests an innovative framework that integrates healthcare engineering, chaotic encryption, and artificial intelligence (AI) to address the privacy issue of medical data. A novel semi-synchronous, decentralized, privacy-enhancing Federated Learning (FL) model built on Convolutional Neural Networks (CNNs) is put forth. The approach integrates federated learning with chaos-based encryption, utilizing the Henon Logistic Crossed Couple Map (HLCML) to strengthen the security of hospital images stored on cloud servers. With its foundation in chaos-based approaches, the encryption algorithm is non-interactive, uses weighted parameters in each aggregation phase, and offers strong privacy protection using semi-synchronous and differential privacy techniques. Extensive simulations demonstrate the algorithm's resilience to various threats, achieving over 85% convergence in privacy-enhanced FL rounds within 100 communication rounds and delivering strong privacy protection with a noise multiplier of ϵ=0.25. Using MobileNetV2 CNN, the framework achieves an average accuracy of 94.3% on non-i.i.d. medical datasets. The HLCML-based encryption protects weight parameters and stops possible data leaks while lowering the computational cost to 0.0143 seconds each round. Theoretical and empirical results confirm the model's capability to enhance privacy for medical institutions and deliver strong performance in non-i.i.d. environments, marking a significant advancement in medical data security. |
| format | Article |
| id | doaj-art-07edabfa435044ecaf15b5a40166905a |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-07edabfa435044ecaf15b5a40166905a2025-01-15T04:11:49ZengElsevierResults in Engineering2590-12302025-03-0125103886A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharingAnimesh Roy0Deva Raj Mahanta1Lipi B. Mahanta2Mathematical & Computational Sciences Division, Institute of Advanced Study in Science and Technology, Guwahati, Assam, 781035, India; Department of Mathematics, SRM Institute of Science and Technology, Kattankulathur, Chennai 603203, IndiaMathematical & Computational Sciences Division, Institute of Advanced Study in Science and Technology, Guwahati, Assam, 781035, IndiaMathematical & Computational Sciences Division, Institute of Advanced Study in Science and Technology, Guwahati, Assam, 781035, India; Corresponding author.Protecting sensitive health information and promoting clinical research depend on medical data security. This paper suggests an innovative framework that integrates healthcare engineering, chaotic encryption, and artificial intelligence (AI) to address the privacy issue of medical data. A novel semi-synchronous, decentralized, privacy-enhancing Federated Learning (FL) model built on Convolutional Neural Networks (CNNs) is put forth. The approach integrates federated learning with chaos-based encryption, utilizing the Henon Logistic Crossed Couple Map (HLCML) to strengthen the security of hospital images stored on cloud servers. With its foundation in chaos-based approaches, the encryption algorithm is non-interactive, uses weighted parameters in each aggregation phase, and offers strong privacy protection using semi-synchronous and differential privacy techniques. Extensive simulations demonstrate the algorithm's resilience to various threats, achieving over 85% convergence in privacy-enhanced FL rounds within 100 communication rounds and delivering strong privacy protection with a noise multiplier of ϵ=0.25. Using MobileNetV2 CNN, the framework achieves an average accuracy of 94.3% on non-i.i.d. medical datasets. The HLCML-based encryption protects weight parameters and stops possible data leaks while lowering the computational cost to 0.0143 seconds each round. Theoretical and empirical results confirm the model's capability to enhance privacy for medical institutions and deliver strong performance in non-i.i.d. environments, marking a significant advancement in medical data security.http://www.sciencedirect.com/science/article/pii/S2590123024021297Chaos-based encryptionDeep learningFederated learningPrivacy-preservingMedical cyber-physical systems (MCPS) |
| spellingShingle | Animesh Roy Deva Raj Mahanta Lipi B. Mahanta A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing Results in Engineering Chaos-based encryption Deep learning Federated learning Privacy-preserving Medical cyber-physical systems (MCPS) |
| title | A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing |
| title_full | A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing |
| title_fullStr | A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing |
| title_full_unstemmed | A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing |
| title_short | A semi-synchronous federated learning framework with chaos-based encryption for enhanced security in medical image sharing |
| title_sort | semi synchronous federated learning framework with chaos based encryption for enhanced security in medical image sharing |
| topic | Chaos-based encryption Deep learning Federated learning Privacy-preserving Medical cyber-physical systems (MCPS) |
| url | http://www.sciencedirect.com/science/article/pii/S2590123024021297 |
| work_keys_str_mv | AT animeshroy asemisynchronousfederatedlearningframeworkwithchaosbasedencryptionforenhancedsecurityinmedicalimagesharing AT devarajmahanta asemisynchronousfederatedlearningframeworkwithchaosbasedencryptionforenhancedsecurityinmedicalimagesharing AT lipibmahanta asemisynchronousfederatedlearningframeworkwithchaosbasedencryptionforenhancedsecurityinmedicalimagesharing AT animeshroy semisynchronousfederatedlearningframeworkwithchaosbasedencryptionforenhancedsecurityinmedicalimagesharing AT devarajmahanta semisynchronousfederatedlearningframeworkwithchaosbasedencryptionforenhancedsecurityinmedicalimagesharing AT lipibmahanta semisynchronousfederatedlearningframeworkwithchaosbasedencryptionforenhancedsecurityinmedicalimagesharing |