Their algorithm is based on splitting the embeddings into a bit-wise representation and then sampling each bit based on the secret key, preserving the same likelihood distribution as with random sampling. (Given that…
Thanks for the correction! Was probably my local bias tending to either cheaper reflectors or using public observatories.
Their algorithm is based on splitting the embeddings into a bit-wise representation and then sampling each bit based on the secret key, preserving the same likelihood distribution as with random sampling. (Given that…
Thanks for the correction! Was probably my local bias tending to either cheaper reflectors or using public observatories.