Enhancing Healthcare Data Security and Privacy through AI-Driven Encryption and Privacy-Preserving Techniques
Dilli Ganesh, R M Bommi, T J Nandhini
Abstract
The use of digital patient data in health management to meet scientific and analytical requirements is now well established, while ensuring the confidentiality and availability of patient information has emerged as a significant issue. The suggested approach is to integrate AI with the traditional encryption techniques to produce a blend of qualitative and automated encryption methods thus making a dynamic encryption environment that adapts with the level of data sensitivity and the kind of users’ access. Furthermore, the approach also incorporate the use of privacy-preserving methodologies including differential privacy, federated learning, and homomorphic encryption, to allow collaboration in the analysis and research of patient data in a more secure manner while preserving the patient’s privacy. The methodology also involves the use of artificial intelligence for intrusion detection and also compliance management to guarantee sustained compliance and security, and legal frameworks including HIPAA, GDPR. The findings of the evaluation show that with the help of the proposed AI-based encryption, it is possible to achieve better security outcomes compared with common methods and reduce the probability of both privacy threats and false alarm violations while enhancing the system’s performance. Additionally, compliance works well to automate the compliance jobs and relieve the healthcare organizations from the time-consuming duties. Naturally, this work presents a robust, and scalable means of protecting healthcare data while at the same time ensuring that the data can still be processed in a manner that benefits the healthcare system.