Abstract: Embodiments are directed to homomorphic encryption for machine learning and neural networks using high-throughput Chinese remainder theorem (CRT) evaluation. An embodiment of an apparatus includes a hardware accelerator to receive a ciphertext generated by homomorphic encryption (HE) for evaluation, decompose coefficients of the ciphertext into a set of decomposed coefficients, multiply the decomposed coefficients using a set of smaller modulus determined based on a larger modulus, and convert results of the multiplying back to an original form corresponding to the larger modulus by performing a reverse Chinese remainder theorem (CRT) transform on the results of multiplying the decomposed coefficients.

Abstract: An accelerator includes polynomial multiplier circuitry including at least one modulus multiplier operating according to a mode. The at least one modulus multiplier include a multiplier to multiply two polynomial coefficients to generate a multiplication result, a power of two reducer to reduce the multiplication result to a reduced multiplication result when the mode is a power of two mode, and a prime modulus reducer to reduce the multiplication result to the reduced multiplication result when the mode is a prime modulus mode.

Abstract: An accelerator includes polynomial multiplier circuitry including at least one modulus multiplier operating according to a mode. The at least one modulus multiplier include a multiplier to multiply two polynomial coefficients to generate a multiplication result, a power of two reducer to reduce the multiplication result to a reduced multiplication result when the mode is a power of two mode, and a prime modulus reducer to reduce the multiplication result to the reduced multiplication result when the mode is a prime modulus mode.

Abstract: Embodiments are directed to homomorphic encryption for machine learning and neural networks using high-throughput Chinese remainder theorem (CRT) evaluation. An embodiment of an apparatus includes a hardware accelerator to receive a ciphertext generated by homomorphic encryption (HE) for evaluation, decompose coefficients of the ciphertext into a set of decomposed coefficients, multiply the decomposed coefficients using a set of smaller modulus determined based on a larger modulus, and convert results of the multiplying back to an original form corresponding to the larger modulus by performing a reverse Chinese remainder theorem (CRT) transform on the results of multiplying the decomposed coefficients.

Abstract: Embodiments are directed to homomorphic encryption for machine learning and neural networks using high-throughput Chinese remainder theorem (CRT) evaluation. An embodiment of an apparatus includes a hardware accelerator to receive a ciphertext generated by homomorphic encryption (HE) for evaluation, decompose coefficients of the ciphertext into a set of decomposed coefficients, multiply the decomposed coefficients using a set of smaller modulus determined based on a larger modulus, and convert results of the multiplying back to an original form corresponding to the larger modulus.

Abstract: Embodiments are directed to homomorphic encryption for machine learning and neural networks using high-throughput Chinese remainder theorem (CRT) evaluation. An embodiment of an apparatus includes a hardware accelerator to receive a ciphertext generated by homomorphic encryption (HE) for evaluation, decompose coefficients of the ciphertext into a set of decomposed coefficients, multiply the decomposed coefficients using a set of smaller modulus determined based on a larger modulus, and convert results of the multiplying back to an original form corresponding to the larger modulus.

Abstract: Embodiments are directed to low circuit depth homomorphic encryption evaluations. An embodiment of an apparatus includes a hardware accelerator to receive a ciphertext generated by homomorphic encryption (HE) for evaluation, determine two coefficients of the ciphertext for HE evaluation, input the two coefficients as a first operand and a second operand to a pipeline multiplier for low circuit depth HE evaluation, perform combinatorial multiplication between the first operand and portions of the second operand, accumulate results of the combinatorial multiplication at each stage of the pipeline multiplier, and perform reduction with Mersenne prime modulus on a resulting accumulated output of the combinatorial multipliers of the pipeline multiplier.

Abstract: A technique includes generating a direct anonymous attestation (DAA)-based signature to prove an electronic device is a member of a group. Generating the signature includes determining a reciprocal of a prime modulus, and determining the reciprocal of the prime modulus comprises left bit shifting a Barrett multiplier by a predetermined number of bits and multiplying a result of the left bit shifting of the Barrett multiplier with the prime modulus.

Abstract: A technique includes generating a direct anonymous attestation (DAA)-based signature to prove an electronic device is a member of a group. Generating the signature includes determining a reciprocal of a prime modulus, and determining the reciprocal of the prime modulus comprises left bit shifting a Barrett multiplier by a predetermined number of bits and multiplying a result of the left bit shifting of the Barrett multiplier with the prime modulus.