Abstract:
A biometric authentication method for a computer system, the computer system comprising: a computer; and an authentication server, the biometric authentication method including steps of: extracting a first feature from the captured biometric information; generating a template polynomial for enrollment; extracting a second feature from the captured biometric information; generating a template polynomial for authentication; generating a correlation function for calculating a correlation between the template polynomial for authentication and the enrolled template polynomial; calculating a correlation value between the template polynomial for authentication and the enrolled template polynomial by using the generated correlation function, and determining based on the calculated correlation value whether or not the biometric information at the time of authentication coincides with the biometric information enrolled.
Abstract:
A machine learning system includes: a server holding a common model; and a plurality of clients each holding concealment target data and an individual model, the server transmits the common model to the plurality of clients, each of the plurality of clients: generates a learning result obtained by updating the common model based on the concealment target data and the individual model held by itself; and transmits the generated learning result to the server, and the server updates the common model based on the received learning result.
Abstract:
A first computer, in data registration processing: determines a type of biometric information for encryption with which the data is to be encrypted; acquires the determined type of biometric information for encryption from a user of the first computer; generates, from each piece of the acquired biometric information for encryption, a public key based on a predetermined algorithm; transmits the public key to a second computer; and transmits the data encrypted with the public key to the third computer, the first computer, in data presentation processing: acquires the encrypted data from a third computer; acquires the determined type of biometric information for decryption from the user of the first computer; generates, from each piece of the acquired biometric information for decryption, a private key based on the predetermined algorithm; decrypts the encrypted data with use of the private key; and presents each piece of the decrypted registered data.
Abstract:
This biometric signature system comprises: a biometric certificate storage module that stores a biometric certificate generated on the basis of a user's biometric information; a biometric information acquisition module that acquires new biometric information from the user; a biometric certificate generation module that generates a new biometric certificate on the basis of the new biometric information; a biometric signature generation module that assigns a biometric signature to the new biometric certificate on the basis of the new biometric information; a biometric signature verification module that verifies the biometric signature using the biometric certificate stored in the biometric certificate storage module; and a biometric certificate registration module that registers the new biometric certificate in the biometric certificate storage module if verification of the biometric signature was successful.
Abstract:
A signature generation and verification system including a signature generation apparatus and a signature verification apparatus is provided. Based on signer certification information possessed by a signer, the signature generation apparatus generates a digital signature and verification data corresponding to a given electronic document and outputs the set of the digital signature and the verification data as signature data. Upon receipt of the electronic document and the signature data, the signature verification apparatus verifies the digital signature using the verification data to verify the integrity of the electronic document. As needed, the signature verification apparatus performs user identification ex-post facto by authenticating that the signer certification information from which the verification data was generated belongs to a legitimate user without knowledge of the signer certification information.
Abstract:
A training server classifies a common model and an individual model transmitted from a plurality of client devices on the basis of the individual model transmitted from a training data management server, and updates the common model and the individual model in accordance with a classification result.
Abstract:
In a particle beam irradiation system, upon receipt of a signal to stop irradiation of a charged particle beam, the signal outputted from a scanning controller, an accelerator and transport system controller stops emission of the charged particle beam from a charged particle beam generation unit to the irradiation unit, the scanning controller determines, according to an irradiation dose of the charged particle beam at one of a plurality of spots that has been irradiated with the charged particle beam until immediately before the accelerator and transport system controller stops the emission, the irradiation dose measured by the irradiation dose monitor from when the signal to stop the irradiation is outputted, whether or not to skip the irradiation of the charged particle beam at another one of the plurality of spots subsequent to the one of the plurality of spots, so as to control the accelerator and transport system controller.
Abstract:
A biometric signature system holds a first template indicating a result of transforming, by predetermined transformation, first biometric information acquired from a predetermined part of a user; and a second template indicating a result of transforming, by predetermined one-way transformation, second biometric information acquired from the predetermined part of the user, identifies a parameter for which a similarity between the first template of the person to be authenticated corrected, generates a second template of the person to be authenticated from each piece of corrected second biometric information, and determines whether authentication of the person to be authenticated is successful by comparing each generated second template with the second template.
Abstract:
A biometric signature system generates a digital signature for electronic documents using biometric information as a secret key. Registration commitment information is generated by performing expansion conversion on a predetermined secret key and embedding the resulting secret key in feature data of biometric information of a user, and a set with a corresponding public key. A pair of one-time secret and public keys is generated for digital signature feature data of the biometric information of the user, and a digital signature for a message is generated using the one-time secret key. A digital signature commitment is generated and a set of the one-time public key and the digital signature is output as the biometric digital signature. The digital signature is verified using the one-time public key. A differential secret key is calculated and a correspondence of the differential secret key, the one-time public key and the public key is verified.
Abstract:
A key generation apparatus for accomplishing high precision authentication in biometric encryption and biometric signing based on feature vectors in a high-dimensional Euclidean space, the apparatus: holds a first feature vector indicating a feature of first biometric information, and a parameter for identifying one arrangement out of a sphere packing arrangement with a density less than 1 and more than a predetermined value, or a sphere covering arrangement with a density equal to or more than 1 and less than a predetermined value, identifies one arrangement out of the sphere packing arrangement or the sphere covering arrangement based on the parameter; selects a first point included in the identified one arrangement; generates a first key by predetermined first conversion on the first point; and generates, based on the first feature vector and the first point, a template associated with the first biometric information.