Secure Medical Image Encryption Using Homomorphic Techniques
K Megala, J Jayadevi, K. Keerthika, G. Manikandan, Vijay Sai R, Balakrishnan Srinivasan · 2024
The security of private medical data is crucial in the age of digital healthcare, especially when it comes to imaging tests like X-rays and ECGs. In addition to jeopardizing patient privacy, unauthorized access to such data also raises questions regarding the veracity of the data. A strong cryptographic architecture for safely encrypting and decrypting medical imaging data is provided to overcome these issues. The method employs homomorphic encryption, a cutting-edge cryptographic technology, to protect medical image integrity and confidentiality during transmission. The system relies heavily on key creation, and keys are generated securely and efficiently by using the ResNet50 architecture, a deep-learning convolutional neural network (CNN), using which high-level features may be extracted from medical images. These features are then converted into cryptographic keys, which will be shared with the receiver. In the final analysis, it has been discovered that the execution time for processing various images stays within an acceptable range after examining a variety of medical image samples. The aim is to protect patient privacy and data integrity while enabling the safe storage and transfer of sensitive medical data.