Abstract: Some embodiments are directed to a computer-implemented method for converting a first computation network of operations arranged to compute a function into a second computation network of FHE operations arranged to compute the same function. For example, a set of expansion factors (?i) may be determined for matrix operations in the first computation network. Real-valued matrices may be converted by scaling the real-valued matrices with their corresponding expansion factor and rounding. An accuracy measure for the second computation network can be iteratively optimized.

Abstract: Some embodiments are directed to a computer-implemented method (500) of determining a set of coefficients for homomorphically multiplying an encrypted value by a scalar. The encrypted value is represented by multiple respective value ciphertexts encrypting the value multiplied by respective powers of an even radix. The scalar multiplication is performed as a linear combination of the multiple respective value ciphertexts according to the set of coefficients. The set of coefficients are determined as digits of a radix decomposition of the scalar with respect to the radix. The determined digits lie between minus half the radix, inclusive, and plus half the radix, inclusive. It is ensured that no two subsequent digits are both equal in absolute value to half the radix.

Abstract: Some embodiments are directed to a fully homomorphic encryption (FHE) cryptography, wherein some encrypted data items are clipped, thereby reducing a bit-size of the encrypted data item and increasing an associated noise level of the encrypted data item. An FHE operation or a decrypt operation that operates on the clipped encrypted data item as input, has noise tolerance above a noise level associated with the clipped encrypted data item.