In just a few years, Fully Homomorphic Encryption (FHE) has gone from a theoretical “holy grail” of cryptography to a commercial product. This is in part due to the development of Machine Learning as a Service, and the fact that our society has evolved to be data-driven. As a consequence, secure computation has become more valuable and has seen some great advances. In this talk, we will discuss some of these improvements in FHE, as well as some of the latest implementation results. We will finish by discuss one of the main challenges in FHE, the analysis of the noise growth in an FHE ciphertext.
I recently joined the ISG group at Royal Holloway as a postdoc researcher. Previously, I spent a year at Intel as a research scientist, working on Privacy-Preserving Machine Learning (PPML). Even before that, I was a PhD student at Bristol University, from where I obtained my PhD in 2018. I work on privacy-preserving machine learning, fully homomorphic encryption and more broadly, computing on encrypted data, lattice-based and post-quantum cryptography.