In the confidential information processing server, when the processing query execution unit receives a processing request, the TEE trusted part processing unit generates a confidential extraction query for extracting data that matches with a condition of a processing target in the processing request by confidential extraction based on the processing request and an encryption key that can be used only in a TEE trusted part, the confidential extraction processing unit instructs execution of the confidential extraction query so as to extract encrypted data of the processing target while the data is kept encrypted from the encryption DB unit, the TEE trusted part processing unit decrypts the encrypted data of the processing target extracted by the confidential extraction processing unit with an encryption key, and executes data processing requested by the processing request, and the processing query execution unit returns an execution result of the data processing to a transmission source of the processing request.

A method for creating a hierarchical threshold signature digital asset wallet using a hierarchical distributed key generator (DKG) and a signature protocol includes steps of generating a public key by users and the digital asset wallet service platform, securing and controlling a portion of shares, sending a transaction signing request, validating the transaction signing request, creating a signature of the signed transaction, and uploading the signed transaction to the corresponding digital asset blockchain network and monitoring the execution of the signed transaction.

A computing system can include a plurality of clients located outside a cloud-based computing environment, where each of the clients may be configured to encode respective original data with a respective unique secret key to generate data hypervectors that encode the original data. A collaborative machine learning system can operate in the cloud-based computing environment and can be operatively coupled to the plurality of clients, where the collaborative machine learning system can be configured to operate on the data hypervectors that encode the original data to train a machine learning model operated by the collaborative machine learning system or to generate an inference from the machine learning model.

A processor-implemented encryption method using homomorphic encryption includes: receiving data; generating a ciphertext by encrypting the received data; determining a coefficient of an approximating polynomial for performing a modular reduction on a modulus corresponding to the ciphertext, based on an error between the approximating polynomial and a modular reduction function; and performing bootstrapping on the ciphertext by performing the modular reduction based on the determined coefficient of the approximating polynomial.

A homomorphic encryption-based testing computing system provides a risk-based, automated, one-directional push of production data through a homomorphic encryption tool and distributes the encrypted data to use in testing of applications. Data elements and test requirements are considered when automatically selecting a homomorphic encryption algorithm. A decisioning component selects an algorithm to use to homomorphically encrypt the data set and a push mechanism performs one or both of the homomorphic encryption and distribution of the encrypted data set to at least one intended host. Once delivered, the testing software and/or testing procedures proceed using the encrypted data set, where results of the testing may be stored in a data store. A validation mechanism may validate the test data against production data and communicates whether testing was successful.

This disclosure provides a method, apparatus and computer program product to create a full homomorphic encryption (FHE)-friendly machine learning model. The approach herein leverages a knowledge distillation framework wherein the FHE-friendly (student) ML model closely mimics the predictions of a more complex (teacher) model, wherein the teacher model is one that, relative to the student model, is more complex and that is pre-trained on large datasets. In the approach herein, the distillation framework uses the more complex teacher model to facilitate training of the FHE-friendly model, but using synthetically-generated training data in lieu of the original datasets used to train the teacher.

Some embodiments enable distributing data (e.g., recorded video, photographs, recorded audio, etc.) to a plurality of users in a manner which preserves the privacy of the respective users. Some embodiments leverage homomorphic encryption and proxy re-encryption techniques to manipulate the respective data so that selected portions of it are revealed according to an identity of the user currently accessing the respective data.

Example selector derived encryption methods and systems include creating a hashed and encrypted database, as well as performing a query against the hashed and encrypted database using an encrypted selector exchange protocol to prevent the exposure of extraneous data from the hashed and encrypted database.

Disclosed is a method for each party of a group of m parties to be able to learn an Nth smallest value in a combined list. The method includes providing a value R.sub.i to a group of members; computing how many numbers are smaller than R.sub.i in a respective list of values for each respective member of the group of members; computing, a total number of smaller values (P.sub.i); identifying a position of R.sub.i in a combined list of values comprising each respective list of values; when N=P.sub.i+1, returning R.sub.i; when N is greater than P.sub.i+1, removing all values smaller than R.sub.i in their respective list of values and setting N=N−(P.sub.i+1); when N is less than P.sub.i+1, removing all numbers bigger than R.sub.i in their respective list of value; and setting i=i+1.

New and efficient protocols are provided for privacy-preserving machine learning training (e.g., for linear regression, logistic regression and neural network using the stochastic gradient descent method). A protocols can use the two-server model, where data owners distribute their private data among two non-colluding servers, which train various models on the joint data using secure two-party computation (2PC). New techniques support secure arithmetic operations on shared decimal numbers, and propose MPC-friendly alternatives to non-linear functions, such as sigmoid and softmax.