Abstract: A method for comparing a first and a second databases to determine whether an individual is represented by both an element of the first database and an element of the second database, wherein said elements are biometric data, including the implementation of the steps applying a classification model for each element of each database so as to construct a set of first and second bins of the respective first and second databases, each bin bringing together similar elements, each first bin being associated with a second bin; comparing the elements from the first database for at least one pair of an associated first bin and second bin belonging to said first bin with the elements from the second database belonging to said second bin, at least one of the first and the second databases then being encrypted homomorphically.

Abstract: A distributed-computing method for computing a metric f(X,Y) representative of a difference between a datum X comprising n bits (x1, . . . , xn) and a datum Y, the metric f(X,Y) taking the form f(X,Y)=fX(X)+?i=1nfi(xi,Y)+fY(Y), the method being implemented by a system comprising m+1 devices and including for any j ranging from 1 to m, computing, by way of the device of index j, at least one intermediate datum depending on the datum X and on the datum Y, and transmitting to the device of index m+1 at least one result comprising or depending on each intermediate datum, and determining, by way of the device of index m+1, the metric f(X,Y), the determining comprising summing each result to obtain a value equal to ?i=1nfi(xi,Y) or a value equal to ?i=1nfi(xi,Y)+fY(Y).

Abstract: The present invention concerns a method for learning the parameters of a convolutional neural network, CNN, for data classification, the method comprising the implementation of steps by data processing means (11a, 11 b, 11c) of at least one server (1a, 1b, 1c), of: (a1) Learning, from a base of already-classified confidential learning data, the parameters of a first CNN; (a2) Learning, from a base of already-classified public learning data, the parameters of a last fully-connected layer (FC) of a second CNN corresponding to the first CNN to which said fully-connected layer (FC) has been added. The present invention also concerns a method for classifying an input datum.

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 authentication or identification of an individual, comprising the implementation by data processing means (11) of a terminal (1) of the following steps: (a) Obtaining of a visible image, an infrared image and a depth image on each of which a biometric feature of said individual appears; (b) Selection of at least one of said visible images, infrared image and depth image depending on the ambient lighting conditions; (c) Detection of said biometric feature of the individual in each image selected; (d) Fusion of the biometric feature(s) detected; and, (e) Authentication or identification of said individual on the basis of the result of the fusion of the biometric feature(s) detected.

Abstract: A method for checking the identity of a reference individual, the method comprising the following steps, implemented by a checking device: selecting terminals respectively associated with individuals forming part of a set of individuals whose identities are intended to be checked by the checking device, the individual forming part of the set of individuals; sending, to each of the selected terminals, an input datum associated with the reference individual and a request asking the terminal to implement a first cryptographic processing operation producing an output datum from the input datum and from a private key specific to the individual associated with the terminal; receiving each output datum; and implementing a second cryptographic processing operation producing a check result relating to the reference individual from each output datum.

Abstract: The present invention relates to a method for learning parameters of a convolutional neural network, CNN, for data classification, the method comprising the implementation, by means for processing data (11) of a server (1), of steps consisting of: (a1) Learning, from an already classified learning database, the parameters of a CNN, called quantized CNN, such that said parameters are valued in a discrete space; (a2) Generating a white-box implementation of at least one layer of said quantized CNN, said white-box implementation being predetermined based on at least one of said learned parameters. The present invention also relates to a method for classifying an input datum.

Abstract: A method for processing personal data, comprising the steps of: (a) For each reference personal data of a reference personal database, calculating in the encrypted domain a similarity rate of the reference personal data with a candidate personal data; said reference personal database being associated with a first partition into a plurality of first sets of reference personal data, and with a second partition into a plurality of second sets of reference personal data, such that each reference personal data of a reference personal database belongs to a single first set and a single second set; (b) For each first set and each second set, calculating an overall similarity rate of said set based on the similarity rates of the reference personal data of said set; (c) Comparing each overall similarity rate of a first and second set with a first and second predetermined threshold, respectively.

Abstract: A method of secure classification of input data by a convolutional neural network (CNN), including (a) determination, by application of the CNN to the input data, of a first classification vector associating with each of a plurality of potential classes a representative integer score of the probability of the input data belonging to the potential class, the first vector corresponding to one possible vector, each possible vector of the first set associating with each of the plurality of potential classes an integer score; (b) construction, from the first vector, of a second classification vector of the input data, such that the second vector also belongs to the first space of possible vectors and has a distance with the first vector according to a given distance function equal to a non-zero reference distance; and return of the second vector as result of the secure classification.

Abstract: A method for comparing a first and a second databases to determine whether an individual is represented by both an element of the first database and an element of the second database, wherein said elements are biometric data, including the implementation of the steps applying a classification model for each element of each database so as to construct a set of first and second bins of the respective first and second databases, each bin bringing together similar elements, each first bin being associated with a second bin; comparing the elements from the first database for at least one pair of an associated first bin and second bin belonging to said first bin with the elements from the second database belonging to said second bin, at least one of the first and the second databases then being encrypted homomorphically.

Abstract: The invention proposes a method for processing personal data, having the steps of (a) Functional encryption of candidate personal data using a functional encryption public key, (b) For at least one reference personal data, functional decryption of the encrypted candidate biometric data using a functional decryption private key for the polynomial function of degree 1 or 2 parameterized with said reference personal data.

Abstract: The present invention relates to a parameter training method for a convolutional neural network, CNN, for classifying data, the method comprising the implementation by data processing means (11c) of servers (1a, 1b, 1c) of steps of: (a1) Obtaining parameters of a set of at least one first CNN; (a2) For a first CNN of said set: Training, based on a database of already-classified public training data, parameters of a final representation block (B) of a second CNN corresponding to the first selected CNN to which said representation block (B) has been added; Retraining, based on a database of already-classified confidential training data of a secondary server (1a, 1b), parameters of the second CNN; Transmitting to the main server (1c) parameters of a third CNN corresponding to the second CNN without a final representation block (B); (a3) Replacing a first CNN of said set of first CNNs with the third CNN; (a4) Aggregating said set of at least one first CNN into a fourth CNN.

Abstract: A method for authentication or identification of an individual, comprising the implementation by data processing means (11) of a terminal (1) of the following steps: (a) Obtaining of a visible image, an infrared image and a depth image on each of which a biometric feature of said individual appears; (b) Selection of at least one of said visible images, infrared image and depth image depending on the ambient lighting conditions; (c) Detection of said biometric feature of the individual in each image selected; (d) Fusion of the biometric feature(s) detected; and, (e) Authentication or identification of said individual on the basis of the result of the fusion of the biometric feature(s) detected.

Abstract: A method for processing a stream of video images to search for information therein, in particular detect predefined objects and/or a motion, comprising the steps of: a) supplying at least one attention map in at least one space of the positions and of the scales of at least one image of the video stream, b) selecting, in this space, points to be analyzed by making the selection depend at least on the values of the coefficients of the attention map at these points, at least some of the points to be analyzed being selected by random draw with a probability of selection in the draw at a point depending on the value of the attention map at that point, a bias being introduced into the map to give a non-zero probability of selection at any point, c) analyzing the selected points to search therein for said information, d) updating the attention map at least for the processing of the subsequent image, from at least the result of the analysis performed in c), e) reiterating the steps a) to d) for each new image of

Abstract: The present invention relates to a parameter training method for a convolutional neural network, CNN, for classifying data, the method comprising the implementation by data processing means (11c) of servers (1a, 1b, 1c) of steps of: (a1) Obtaining parameters of a set of at least one first CNN; (a2) For a first CNN of said set: Training, based on a database of already-classified public training data, parameters of a final representation block (B) of a second CNN corresponding to the first selected CNN to which said representation block (B) has been added; Retraining, based on a database of already-classified confidential training data of a secondary server (1a, 1b), parameters of the second CNN; Transmitting to the main server (1c) parameters of a third CNN corresponding to the second CNN without a final representation block (B); (a3) Replacing a first CNN of said set of first CNNs with the third CNN; (a4) Aggregating said set of at least one first CNN into a fourth CNN.

Abstract: The present invention relates to a method of secure classification of an input data by means of a convolutional neural network, CNN, the method comprising the implementation by data processing means (11a, 11b, 11c, 21) of at least one device (1a, 1b, 1c, 2), of steps of: (a) Determination, by application of said CNN to said input data, of a first classification vector of said input data associating with each of a plurality of potential classes a representative integer score of the probability of said input data belonging to the potential class, the first vector corresponding to one possible vector among a first finite and countable set of possible vectors, each possible vector of the first set associating with each of the plurality of potential classes an integer score such that said scores of the possible vector constitute a composition of a predefined whole total value; (b) Construction, from the first vector, of a second classification vector of said input data, such that the second vector also belongs to

Abstract: A method for processing a stream of video images to search for information therein, in particular detect predefined objects and/or a motion, comprising the steps of: a) supplying at least one attention map in at least one space of the positions and of the scales of at least one image of the video stream, b) selecting, in this space, points to be analyzed by making the selection depend at least on the values of the coefficients of the attention map at these points, at least some of the points to be analyzed being selected by random draw with a probability of selection in the draw at a point depending on the value of the attention map at that point, a bias being introduced into the map to give a non-zero probability of selection at any point, c) analyzing the selected points to search therein for said information, d) updating the attention map at least for the processing of the subsequent image, from at least the result of the analysis performed in c), e) reiterating the steps a) to d) for each new image of

Abstract: The present invention concerns a method for learning the parameters of a convolutional neural network, CNN, for data classification, the method comprising the implementation of steps by data processing means (11a, 11 b, 11c) of at least one server (1a, 1b, 1c), of: (a1) Learning, from a base of already-classified confidential learning data, the parameters of a first CNN; (a2) Learning, from a base of already-classified public learning data, the parameters of a last fully-connected layer (FC) of a second CNN corresponding to the first CNN to which said fully-connected layer (FC) has been added. The present invention also concerns a method for classifying an input datum.

Abstract: The present invention relates to a method for learning parameters of a convolutional neural network, CNN, for data classification, the method comprising the implementation, by means for processing data (11) of a server (1), of steps consisting of: (a1) Learning, from an already classified learning database, the parameters of a CNN, called quantized CNN, such that said parameters are valued in a discrete space; (a2) Generating a white-box implementation of at least one layer of said quantized CNN, said white-box implementation being predetermined based on at least one of said learned parameters. The present invention also relates to a method for classifying an input datum.

Abstract: Image processing system (I1, . . . In), including a main neural network (2) and, upstream thereof, a preprocessing module (3) including several neural networks (R1, . . . , Rn) working in parallel to process several starting images of the same object and configured to generate, by fusing the outputs of these networks, a representation (D) of the object improving the performance of the main neural network, the learning of the neural networks of the preprocessing module (3) being performed at least partly simultaneously with the one of the main neural network (2).