Abstract: A verification apparatus acquires a source code for multiparty computation, while changing a combination of options settable to a multiparty computation compiler, compiles the source code for each combination of options to generate a plurality of multiparty computation executable codes, selects at least one multiparty computation executable code from the plurality of multiparty computation executable codes as a verification code and provides the at least one verification code to a verification environment of multiparty computation, generates an evaluation index with respect to an execution result of at least one verification code in the verification environment, and selects at least one recommended code from the plurality of multiparty computation executable codes, based on the evaluation index corresponding to at least one verification code and outputs the selected recommended code.

Abstract: An information processing acquires biometric information of a plurality of persons. The information processing generates one adversarial example, using the biometric information of the plurality of persons.

Abstract: Calculate a plurality of feature vectors representing features of an input sample from the input sample which is multidimensional data by using a plurality of feature calculation models. Calculate similarity between an average value of the plurality of feature vectors and a representative vector corresponding to a class to which the input sample belongs among a plurality of representative vectors corresponding to a plurality of classes respectively, the representative vector having same dimensionality as each of the plurality of feature vectors. Learn parameters of the plurality of feature calculation models based on an evaluation function in which a value is larger as the similarity between the average value of the plurality of feature vectors and the representative vector corresponding to the class to which the input sample belongs is smaller.

Abstract: A learning device includes: an incorrect answer prediction calculation unit which obtains incorrect answer class prediction probability vectors by excluding a correct answer class element from prediction probability vectors of neural network models for supervised learning data; and an updating unit which performs learning of two of the neural network models so as to further reduce a value of an objective function which includes a diversity function, a value of diversity function decreasing as an angle between the incorrect answer class prediction probability vectors of the two neural network models increases.

Abstract: An adversarial example detection device includes a first feature extraction unit configured to extract first features with respect to input data and comparative data in a first calculation method, a second feature extraction unit configured to extract second features with respect to the input data and the comparative data in a second calculation method different from the first calculation method, and a determination unit configured to determine whether or not at least one piece of the input data and the comparative data is an adversarial example through calculation using the first features and the second features.

Abstract: A robust learning device is a learning device that, with a parameter of n neural networks, training data, and a correct label serving as inputs, outputs the updated parameter, including: a model selection unit that selects neural networks, which are less than n and equal to or more than two, among the n neural networks; a limited objective function calculation unit that calculates, in a calculation process of an objective function including a process in which a value of the objective function becomes smaller as an output of the neural networks to the training data is closer to the correct label and a degree of similarity between the neural networks is smaller, a limited objective function including only the process relating to the neural networks selected by the model selection unit; and an update unit that updates the parameter such that a value of the limited objective function is decreased.

Abstract: A secure computation server includes: a computation processing part that performs secure computation by using data x received from a client and computes a computation result R; and a trail registration part that makes a predetermined trail storage system to store first trail data for certifying identity of the data x, the first trail data having been calculated from the data x, and second trail data for certifying a relationship between the data x and the computation result R. The predetermined trail storage system manages the first and second trail data in a non-rewritable manner and provides the first and second trail data to a predetermined audit node.

Abstract: A learning apparatus includes: a prediction loss calculating device that calculates a prediction loss function based on an error between outputs of machine learning models to which training data is inputted and a ground truth label; a gradient loss calculating device that calculates a gradient loss function based on a gradient of the prediction loss function; and an updating device that performs an update operation of updating the machine learning models on the basis of the prediction loss function and the gradient loss function, the gradient loss calculating device calculates the gradient loss function based on the gradient when the number of times which the update operation is performed is smaller than a predetermined number, and calculates a function that represents zero as the gradient loss function when the number of times which the update operation is performed is larger than the predetermined number.

Abstract: There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, whe

Abstract: An information processing apparatus that performs bit embedding processing by four-party MPC using 2-out-of-4 replicated secret sharing stores a seed to generate a random number used when performing an operation concerning shares, generates, by using the seed, share reconstruction data for reconstructing a share used when performing bit embedding, and constructs a share for bit embedding by using at least the share reconstruction data.

Abstract: There is provided an information processing apparatus that executes efficient type conversion processing in four-party computation using 2-out-of-4 replicated secret sharing. The information processing apparatus comprises a basic operation seed storage part, a reshare value computation part, and a share construction part. The basic operation seed storage part stores a seed for generating a random number used when computation is performed on a share. The reshare value computation part generates a random number using the seed, computes a share reshare value using the generated random number, and transmits data regarding the generated random number to other apparatuses. The share construction part constructs a share for type conversion using the data regarding the generated random number and the share reshare value received from other apparatuses.

Abstract: There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, whe

Abstract: A verification apparatus acquires a source code for multiparty computation, while changing a combination of options settable to a multiparty computation compiler, compiles the source code for each combination of options to generate a plurality of multiparty computation executable codes, selects at least one multiparty computation executable code from the plurality of multiparty computation executable codes as a verification code and provides the at least one verification code to a verification environment of multiparty computation, generates an evaluation index with respect to an execution result of at least one verification code in the verification environment, and selects at least one recommended code from the plurality of multiparty computation executable codes, based on the evaluation index corresponding to at least one verification code and outputs the selected recommended code.

Abstract: There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, whe