US 12,388,617 B2
Private artificial neural networks with trusted execution environments and quadratic homomorphic encryption
Claudio Soriente, Heidelberg (DE); and Dario Fiore, Pozuelo de Alarcon (ES)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 18/280,966
Filed by NEC Laboratories Europe GmbH, Heidelberg (DE)
PCT Filed May 19, 2021, PCT No. PCT/EP2021/063353
§ 371(c)(1), (2) Date Sep. 8, 2023,
PCT Pub. No. WO2022/199861, PCT Pub. Date Sep. 29, 2022.
Claims priority of application No. 21164884 (EP), filed on Mar. 25, 2021.
Prior Publication US 2025/0030536 A1, Jan. 23, 2025
Int. Cl. H04L 29/06 (2006.01); G06N 3/084 (2023.01); H04L 9/00 (2022.01); H04L 9/30 (2006.01)
CPC H04L 9/008 (2013.01) [G06N 3/084 (2013.01); H04L 9/3073 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A computer-implemented method of training an artificial neural network (ANN) on a remote host, the method comprising:
computing, by a trusted process deployed in a trusted execution environment (TEE) on the remote host, a key-pair for a homomorphic encryption scheme and sharing, by the trusted process, the public key (PK) of the key-pair with an untrusted process deployed on the remote host; and
splitting the training procedure of the ANN between the untrusted process and the trusted process, wherein the untrusted process computes encrypted inputs to neurons of the ANN by means of the homomorphic encryption scheme, while the trusted process computes outputs of the neurons based on the respective encrypted inputs to the neurons as provided by the untrusted process.