Nec Corporation

Nec Laboratories Europe Gmbh

Dario Fiore

Claudio Soriente

Antonio Faonio

Miguel Ambrona

Luca Nizzardo

A method training an artificial neural network (ANN) on a remote host computes, using a trusted process deployed in a trusted execution environment (TEE) on the remote host, a key-pair for a homomorphic encryption scheme and shares, by the trusted process, the public key (PK) of the key-pair with an untrusted process deployed on the remote host. The method splits 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.

Private artificial neural networks with trusted execution environments and quadratic homomorphic encryption

A method for performing computation of a function over encrypted data by a computation entity is provided. According to the method, the computation of a quadratic function is performed by the computation entity, the encrypted data are encrypted by a linearly homomorphic encryption scheme, and a homomorphic message authentication code is used for providing verifiable computation on encrypted data.

Method and computation entity for performing computation of a function over encrypted data

In a system having a plurality of servers, a method is executed to perform an encryption scheme. The method includes a server of the plurality of servers receiving a request token to compute a function on a data point, the data point being encrypted as a ciphertext and the request token being based on the ciphertext and the function. The server grants the request to compute the function on the datapoint by sending a function evaluation key, and participates in a distributed decryption protocol for determining a result of computing the function on the data point by sending a master secret key.

Method and system for multi-authority controlled functional encryption

A computer-implemented method includes receiving an original message from a trusted execution environment. The original message includes an original digital signature authored by the trusted execution environment. The method includes computing a proof of knowledge for the original digital signature and modifying the original message by replacing the original digital signature with the proof of knowledge.

Growing community of inventors

Madrid, Spain

Dario Fiore