A computer-implemented method for providing a distributed data processing service for performing a secure multiparty computation of a function on at least first and second items of private input data using at least a first and a second computing engine communicatively coupled via a communication network.

In a secure multi-party computation (sMPC) system, a super mask is constructed using a set of masks corresponding to a set of data contributors. Each data contributor uses a corresponding different mask to obfuscate the data of the data contributor. a first scaled masked data is formed by applying a first scale factor to first masked data of the first data contributor, the scale factor being computed specifically for the first data contributor from the super mask. A union is constructed of all scaled masked data from all data contributors, including the first scaled masked data. A machine learning (ML) model is trained using the union as training data, where the union continues to keep obfuscated the differently masked data from the different data contributors. The training produces a trained ML model usable in the sMPC with the set of data contributors.

Certain aspects of the present disclosure provide techniques for performing computations on encrypted data. One example method generally includes obtaining, at a computing device, encrypted data, wherein the encrypted data is encrypted using fully homomorphic encryption and performing at least one computation on the encrypted data while the encrypted data remains encrypted. The method further includes identifying a clear data operation to perform on the encrypted data and transmitting, from the computing device to a server, a request to perform the clear data operation on the encrypted data, wherein the request includes the encrypted data. The method further includes receiving, at the computing device in response to the request, encrypted output from the server, wherein the encrypted output is of the same size and the same format for all encrypted data transmitted to the server.

A distributed computer network utilizing cryptography that includes one or more processors, wherein the one or more processors are programmed to receive a secret input state and one or more tuples, mask the secret input state with the one or more tuple and utilize a reveal to compute a masked input, compute six multiplications on the masked input, compute multiplication of two secret values to output an intermediate output, mask a third secret value from the intermediate output and reveal the third secret value to compute an interaction, compute a multiparty-computation multiplication with the interaction, and output a final secret value in response to computing the multiparty-computation multiplication.

A multi-party network utilizing cryptography that includes one or more processors, wherein the one or more processors are programmed to utilize bit decomposition on an embedded input state associated with an input, apply a backward substitution box affine transformation to output bits, determine seven powers from the output bits utilizing seven of linear transformations, determine an inverse of the secret state utilizing six secret-by-secret multiplications with the seven powers from the output bits, and output an inverse of a secret input state of a Galois field in response to composing the inverse of the secret state.

Provided herein are system, devices and methods for applying Multi-Party Computation (MPC) to authenticate a user accessing a secure resource using a plurality of computing nodes. The computing nodes, each receiving a respective one of a plurality of encrypted shares created using a plurality of keys to encrypt private data captured by a client device used by the user accessing the secure resource, engage in a secure MPC to compare between the encrypted shares and reference encrypted private data copies also encrypted using the plurality of keys without decrypting the private data since the keys are not available to the computing nodes. The computing nodes compute a match score based on the comparison and transmit it to a controller of the secure resource configured to grant or deny the client device access to the secure resource based on the match score.

Disclosed herein are methods and systems for efficiently retrieving data from an at least partially encrypted table based record using secure Multi-Party Computation (MPC). A query received to retrieve data from a table based record comprising data items arranged in rows and columns may include a queried data item (key) which potentially matches one or more encrypted data items contained in one or more of the columns. The computing nodes, each having a respective one of a plurality of shares of a one-hot representation of each of the encrypted data items engage in the MPC session to match between a one-hot representation of the queried data item and the one-hot representation of each encrypted data item and output each matching row. The match is based on multiplying, in each encrypted data item's one-hot representation, only bits identified as hot in the queried data item's one-hot representation.

There are provided systems and methods for shared cryptogram generation during multi-party digital token processing. A service provider, such as an electronic transaction processor for digital transactions, may require tokenized data in order to protect sensitive or secure data, such as payment card data during electronic transaction processing. In this regard, the service provider may tokenize the data, which may require a cryptogram for validation of a corresponding digital token. The cryptogram may be generated based on input from multiple participants to the transaction, where a length of the cryptogram may be determined based on a risk score for the transaction. Each transaction participant may be assigned one or more slots or values in the cryptogram to provide based on the risk score and other rules for cryptogram generation. Each participant may provide corresponding portions, where the service provider may generate and backwards update the participants of the cryptogram.

Aspects of the current subject matter are directed to performing privacy-preserving analytics over sensitive data without sharing plaintext data. According to an aspect, a system includes at least one data processor and at least one memory storing instructions which, when executed by the at least one data processor, result in operations including: receiving, from each of a plurality of clients, a utility score and a partial noise value; performing, based on the received utility scores and the partial noise values, a secure multi-party computation of a privacy-preserving statistic, the performing of the secure multi-party computation of the privacy-preserving statistic further comprising determining a noisy utility score for each data value in a domain of output values and selecting a highest noise utility score from the determined noisy utilities scores; and providing, based on the selected highest utility score, an output value for the privacy-preserving statistic.

Provided are systems for conducting private set intersection (PSI) techniques with multiple parties using a data repository that include at least one processor to generate a data repository, receive, from a submission entity system associated with a submission entity, a private set intersection (PSI) data query that includes a match parameter for performing the PSI data query, transmit, to the submission entity system, a data classification encryption key, wherein the data classification encryption key is associated with a data field that corresponds to a match parameter data field of the match parameter, determine whether to authorize the PSI data query on the data repository, transmit, to the submission entity system, a data authorization encryption key based on determining to authorize the PSI data query on the data repository, and perform the PSI data query on the data repository. Methods and computer program products are also provided.