Abstract: A method for the secure use of a first neural network on an input datum, the method including the implementation, by data processing device of a terminal, of the following steps: (a) constructing a second neural network corresponding to the first neural network, into which is inserted, at the input of a target layer of the first neural network, at least one auto-encoder neural network trained to add a parasitic noise to its input; (b) using the second neural network on the input datum.

Abstract: A method for secure use of a first neural network on an input datum, the method comprising implementing, by data processing circuitry of a terminal: (a) constructing a second neural network which corresponds to the first neural network and receives at least one convolutional neural network approximating the identity function, (b) using the second neural network on the input datum. Further including a method for training parameters of the second neural network.

Abstract: The invention relates to a method for enrolling data in order to verify the authenticity of a security datum, the method comprising implementing by data processing means of a server the steps of: obtaining a reference security datum, generating a first encoded datum by applying to the reference security datum an obfuscated fuzzy Hamming distance encoding procedure, determining from the reference security datum, a plurality of derived data of the reference security datum, generating a first random datum, and determining a second encoded datum such that a variable point comparison predicate parameterized by the second encoded datum and the first random datum is true when said variable point has as coordinates said derived data, storing on a data storage means of the server at least said first and second encoded data. The invention also relates to a verification method and a server for this purpose.

Abstract: Process and system for processing data by an artificial neural network comprising several pooling or convolutional layers all associated with neural matrices, including for each layer of the several successive layers obtaining a reordered matrix, obtaining a division of the reordered matrix into a plurality of contiguous submatrices having given widths and heights, and grouping execution of the individual operations to be performed for each submatrix.