Cloud-based Homomorphic Encryption for Privacy-preserving Machine Learning in Clinical Decision Support.

Homomorphic Encryption (HE) is seen as an emerging privacy-enhancing technology, relying on the property that computations can occur on encrypted data without the need for decryption. This project has developed a technological platform – Homomorphic Encryption Bus (HEB), that provides a uniform, flexible and general approach to cloud-based privacy-preserving system integration. It is uniquely designed to make HE more practical for mainstream clinical application use, equipped with a rich set of capabilities and potentially very complex depth of HE operations. Such a solution would be suitable for the long-term privacy-preserving processing requirements of a cloud-based clinical decision support system, which would typically require complex combinatorial logic, workflow and machine learning capabilities.

Cloud-based Privacy-preserving Computation: Homomorphic Encryption Bus (HEB)

– Computation on encrypted sensitive information eg. for machine learning, logical and workflow tasks using Homomorphic Encryption (HE)

– Long-term, high-precision, highly parallel arithmetic and boolean computation (text processing to come) —

– Limited use of two-party network interactions involving distributed decryption and data obfuscation techniques; overcoming current limitation of HE technologies while maintaining privacy —

– Consistent framework for scalability over the cloud —

– Link to other cryptographic schemes and privacy-enhancing technologies, extending secure computation to other areas eg. IoT

HDR Student – Dr Jim Basilakis

Supervisory Panel – A/Prof. Bahman Javadi, Prof. Simeon Simoff & Prof. Anthony Maeder.