Abstract: Disclosed is a process for testing a suspect model to determine whether it was derived from a source model. An example method includes receiving, from a model owner node, a source model and a fingerprint associated with the source model, receiving a suspect model at a service node, based on a request to test the suspect model, applying the fingerprint to the suspect model to generate an output and, when the output has an accuracy that is equal to or greater than a threshold, determining that the suspect model is derived from the source model. Imperceptible noise can be used to generate the fingerprint which can cause predictable outputs from the source model and a potential derivative thereof.

Abstract: A method includes dividing a plurality of filters in a first layer of a neural network into a first set of filters and a second set of filters, applying each of the first set of filters to an input of the neural network, aggregating, at a second layer of the neural network, a respective one of a first set of outputs with a respective one of a second set of outputs, splitting respective weights of specific neurons activated in each remaining layer, at each specific neuron from each remaining layer, applying a respective filter associated with each specific neuron and a first corresponding weight, obtaining a second set of neuron outputs, for each specific neuron, aggregating one of the first set of neuron outputs with one of a second set of neuron outputs and generating an output of the neural network based on the aggregated neuron outputs.

Abstract: A system and method are disclosed for providing a private multi-modal artificial intelligence platform. The method includes splitting a neural network into a first client-side network, a second client-side network and a server-side network and sending the first client-side network to a first client. The first client-side network processes first data from the first client, the first data having a first type. The method includes sending the second client-side network to a second client. The second client-side network processes second data from the second client, the second data having a second type. The first type and the second type have a common association. Forward and back propagation occurs between the client side networks and disparate data types on the different client side networks and the server-side network to train the neural network.

Abstract: Disclosed is a method that includes training, at a client, a part of a deep learning network up to a split layer of the client. Based on an output of the split layer, the method includes completing, at a server, training of the deep learning network by forward propagating the output received at a split layer of the server to a last layer of the server. The server calculates a weighted loss function for the client at the last layer and stores the calculated loss function. After each respective client of a plurality of clients has a respective loss function stored, the server averages the plurality of respective weighted client loss functions and back propagates gradients based on the average loss value from the last layer of the server to the split layer of the server and transmits just the server split layer gradients to the respective clients.

Abstract: A system and method for securely computing an inference of two types of tree-based models, namely XGBoost and Random Forest, using secure multi-party computation protocol. The method includes computing a respective comparison result of each respective node of a plurality of nodes in a tree classifier. Each node has a respective threshold value. The respective comparison result is based on respective data associated with a data owner device being applied to a respective node having the respective threshold value. The method includes computing, based on the respective comparison result, a leaf value associated with the tree classifier, generating a share of the leaf value and transmitting, to the data owner device, a share of the leaf value. The data owner device computes, using a secure multi-party computation and between the model owner device and the data owner device, the leaf value for the respective data of the data owner.

Abstract: A system and method are disclosed for secure multi-party computations. The system performs operations including establishing an API for coordinating joint operations between a first access point and a second access point related to performing a secure prediction task in which the first access point and the second access point will perform private computation of first data and second data without the parties having access to each other's data. The operations include storing a list of assets representing metadata about the first data and the second data, receiving a selection of the second data for use with the first data, managing an authentication and authorization of communications between the first access point and the second access point and performing the secure prediction task using the second data operating on the first data.

Abstract: A method of providing blind vertical learning includes creating, based on assembled data, a neural network having n bottom portions and a top portion and transmitting each bottom portion of then bottom portions to a client device. The training of the neural network includes accepting a, output from each bottom portion of the neural network, joining the plurality of outputs at a fusion layer, passing the fused outputs to the top portion of the neural network, carrying out a forward propagation step at the top portion of neural network, calculating a loss value after the forward propagation step, calculating a set of gradients of the loss value with respect to server-side model parameters and passing subsets of the set of gradients to a client device. After training, the method includes combining the trained bottom portion from each client device into a combined model.

Abstract: A system and method are disclosed for comparing private sets of data. The method includes encoding first elements of a first data set such that each element of the first data set is assigned a respective number in a first table, encoding second elements of a second data set such that each element of the second data set is assigned a respective number in a second table, applying a private compare function to compute an equality of each row of the first table and the second table to yield an analysis and, based on the analysis, generating a unique index of similar elements between the first data set and the second data set.

Abstract: 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 Ri to a group of members; computing how many numbers are smaller than Ri in a respective list of values for each respective member of the group of members; computing, a total number of smaller values (Pi); identifying a position of Ri in a combined list of values comprising each respective list of values; when N=Pi+1, returning Ri; when N is greater than Pi+1, removing all values smaller than Ri in their respective list of values and setting N=N?(Pi+1); when N is less than Pi+1, removing all numbers bigger than Ri in their respective list of value; and setting i=i+1.

Abstract: Systems, methods, and computer-readable media for achieving privacy for both data and an algorithm that operates on the data. A system can involve receiving an algorithm from an algorithm provider and receiving data from a data provider, dividing the algorithm into a first algorithm subset and a second algorithm subset and dividing the data into a first data subset and a second data subset, sending the first algorithm subset and the first data subset to the algorithm provider and sending the second algorithm subset and the second data subset to the data provider, receiving a first partial result from the algorithm provider based on the first algorithm subset and first data subset and receiving a second partial result from the data provider based on the second algorithm subset and the second data subset, and determining a combined result based on the first partial result and the second partial result.

Abstract: A system and method are disclosed for providing a quantum proof key exchange. The method includes generating at a first computing device a random bit ai, encrypting ai using quantum-proof homomorphic encryption ? to yield ?A(ai), transmitting ?A(ai) to a second computing device, generating at the second computing device a random bit bi, encrypting bi using the quantum-proof homomorphic encryption ? to yield ?B(bi), transmitting ?B(bi) to the first computing device and generating a common key between the first computing device and the second computing device based on ?A(ai) and ?B(bi).

Abstract: A system and method are disclosed for each party of a group of m parties to be able to learn an Nth smallest value in a combined list of the values in which each party has separate lists of values. A method includes creating, by each party of a group of m parties, m lists of additive shares associated with each party's respective list of data, distributing, from each party to each other party in the group of m parties, m?1 of the lists of additive shares to yield a respective combined list of additive shares Wi obtained by each party of the m parties, receiving from a trusted party a list of additive shares Vi associated with a hot-code vector V, computing, in a shared space by each party, a respective Ri value using a secure multiplication protocol and comparing, in the shared space, by each party and using secure multi-party comparison protocol, the respective Ri to all elements in the respective combined list of additive shares Wi to yield a total number Pi of values in Wi that are smaller than Ri.

Abstract: Disclosed is a process for testing a suspect model to determine whether it was derived from a source model. An example method includes receiving, from a model owner node, a source model and a fingerprint associated with the source model, receiving a suspect model at a service node, based on a request to test the suspect model, applying the fingerprint to the suspect model to generate an output and, when the output has an accuracy that is equal to or greater than a threshold, determining that the suspect model is derived from the source model. Imperceptible noise can be used to generate the fingerprint which can cause predictable outputs from the source model and a potential derivative thereof.

Abstract: A system and method are disclosed for providing a privacy-preserving training approach for split learning methods, including blind learning.

Abstract: Disclosed is a system and method of de-identifying data. A method includes splitting, at a first entity, a byte of data of an original record into a first random portion and a second random portion, inserting first random bits into the first random portion to yield a first new byte and inserting second random bits into the second random portion to yield a second new byte. The method then includes transmitting the second new byte to a second entity, receiving, at the first entity, a first portion of an algorithm from the second entity and processing the first new byte by the first portion of the algorithm to yield a first partial result. The first partial result can be combined with a second partial result from the second entity processing the second new byte by a second portion of the algorithm.

Abstract: Disclosed is a method that includes training, at a client, a part of a deep learning network up to a split layer of the client. Based on an output of the split layer, the method includes completing, at a server, training of the deep learning network by forward propagating the output received at a split layer of the server to a last layer of the server. The server calculates a weighted loss function for the client at the last layer and stores the calculated loss function. After each respective client of a plurality of clients has a respective loss function stored, the server averages the plurality of respective weighted client loss functions and back propagates gradients based on the average loss value from the last layer of the server to the split layer of the server and transmits just the server split layer gradients to the respective clients.

Abstract: A method includes receiving, on a computer-implemented system and from user, an identification of data and an identification of an algorithm and, based on a user interaction with the computer-implemented system comprising a one-click interaction or a two-click interaction. Without further user input, the method includes dividing the data into a data first subset and a data second subset, dividing the algorithm (or a Boolean logic gate representation of the algorithm) into an algorithm first subset and an algorithm second subset, running, on the computer-implemented system at a first location, the data first subset with the algorithm first subset to yield a first partial result, running, on the computer-implemented system at a second location separate from the first location, the data second subset with the algorithm second subset to yield a second partial result and outputting a combined result based on the first partial result and the second partial result.

Abstract: A method includes dividing a plurality of filters in a first layer of a neural network into a first set of filters and a second set of filters, applying each of the first set of filters to an input of the neural network, aggregating, at a second layer of the neural network, a respective one of a first set of outputs with a respective one of a second set of outputs, splitting respective weights of specific neurons activated in each remaining layer, at each specific neuron from each remaining layer, applying a respective filter associated with each specific neuron and a first corresponding weight, obtaining a second set of neuron outputs, for each specific neuron, aggregating one of the first set of neuron outputs with one of a second set of neuron outputs and generating an output of the neural network based on the aggregated neuron outputs.