Achieving Efficient and Privacy-Preserving k-NN Query for Outsourced eHealthcare Data.

Area of Science:

• Computer Science
• Healthcare Informatics
• Cybersecurity

Background:

• Internet of Things devices generate vast amounts of sensitive eHealthcare data.
• Cloud computing is utilized for eHealthcare data services like k-NN queries, but raises privacy concerns.
• Existing k-NN query methods over encrypted data are often inefficient and lack robust privacy guarantees.

Purpose of the Study:

• To design an efficient and privacy-preserving k-NN query scheme for encrypted outsourced eHealthcare data.
• To address the dual challenges of data privacy and computational efficiency in cloud-based eHealthcare analytics.
• To enable secure and reliable data services for medical diagnosis using sensitive health information.

Main Methods:

• Integration of k d-tree data structure with homomorphic encryption techniques.
• Development of a scheme for efficient storage of encrypted eHealthcare data in the cloud.
• Implementation of privacy-preserving k-NN query processing over encrypted datasets.

Main Results:

• Achieved a computational complexity of O(l * N^(1/l)) for k-NN queries over encrypted data, outperforming existing methods.
• Demonstrated significant efficiency gains in privacy-preserving k-NN query processing.
• Security analysis confirmed the proposed scheme's privacy-preserving capabilities under a defined security model.

Conclusions:

• The proposed scheme offers an efficient and secure solution for k-NN queries on encrypted eHealthcare data.
• This advancement facilitates reliable data services for doctors while safeguarding sensitive patient information.
• The integration of k d-tree and homomorphic encryption provides a robust framework for secure cloud-based health data analysis.