CoFHE: Compiler for Fully Homomorphic Encryption
In today’s data-driven world, our personal data is frequently shared with enterprises and cloud service providers. Unfortunately, data processing in the cloud is not 100% secure and private. In the year 2022, approximately 4,100 data breaches were publicly reported, resulting in an average cost of $4.35 million per breach with sensitive information compromised for more than 400 million individuals across all breaches. In the past decade, fully homomorphic encryption (FHE) has emerged as a viable cryptographic solution that allows a cloud service provider to protect the data by keeping it in encrypted form the whole time – during transit, at rest, and during processing. In this project, we propose to develop and open-source CoFHE, a comprehensive FHE compiler framework to automate the process of generating the FHE implementations of the machine learning-based cloud applications using the CKKS FHE scheme. The ultimate goal is to ease the adoption of FHE for application developers, and in turn, make FHE pervasive across all cloud providers.