Blog

Fully Homomorphic Encryption (FHE) is a cryptographic primitive that allows one to perform computations on encrypted data. The big efficiency improvements achieved in this primitive in the last few years have fostered the design and development of many... Continue reading

Fully Homomorphic Encryption (FHE) allows one to perform computations on encrypted data, making it particularly useful for providing privacy to computations. The privacy guarantees of FHE schemes can however be threatened by parties with access to a... Continue reading

Shuffle-without-replacement is widely used as a drop-in for Poisson subsampling in DP-SGD — but the two carry very different privacy guarantees, and the gap can... Continue reading

We use fuzzy private set intersection between an individual's images and a training set to determine if their data was used to train a model. Results indicate... Continue reading

zkPi is a tool capable of verifying Lean proofs independently without sharing any information about the inner workings of the proof (zero-knowledge). The... Continue reading

A verified compiler from Boolean circuits to GSW homomorphic encryption circuits, written and proven correct in Lean 4 with Mathlib. Continue reading