[physicsyogi]

Since TFHE does the encryption at the binary level, it looks like it would need to also work on the float level to be useful for a lot of data science/machine learning use cases. I could be wrong though.

[malux85]

If you can do binary, then you can represent floating point numbers, no?

[nindanaoto]

TFHE is known to be switchable between other RLWE based Homomorphic Encryption. https://eprint.iacr.org/2018/758 Glyph applied it to accelerate deep learning, but they use integer level, not float. https://arxiv.org/abs/1911.07101

AFAIK, Homomorphic Encryption which supports floating point arithmetic is not known. Fixed point one is known, CKKS. https://github.com/snucrypto/HEAAN