A computing device includes a processor and a machine-readable storage storing instructions. The instructions are executable by the processor to: receive a bit vector representing input data to be tokenized; divide the bit vector into two vector portions; and perform a plurality of rounds of a Feistel network on the two vector portions, each round including converting one vector portion using a table-based hash function that combines multiple tokens retrieved from at least one token table.

The present invention provides a robust and effective solution to an organization by enabling them to implement a system (110) for facilitating format preserving encryption capability such that the encrypted data will not be available with its original value in a big data system and render sensitive field data as non-sensitive. Thus, sensitive data may be hidden from data-stores/warehouses without worrying about downstream access to the data. The system (110) proposed may also preserve the data type and format of datasets but not limited to the like. The system encrypts a dataset with a unique key (404) and then allows a privileged user (902) to decrypt the encrypted dataset with the unique key (404) and view the decrypted values without getting access to the sensitive original dataset.

A cryptographic circuit performs a substitution operation of a cryptographic algorithm. For each substitution operation of the cryptographic algorithm, a series of substitution operations are performed by the cryptographic circuit. One of the substitution operations of the series is a real substitution operation corresponding to the substitution operation of the cryptographic algorithm. One or more other substitution operations of the series are dummy substitution operations. A position of the real substitution operation in said series is selected randomly.

The present disclosure relates to systems and methods for transmitting data. The methods may include obtaining, by a first module, a first packet, wherein the first packet includes a first random code, first data, and a first signature, wherein the first signature is generated by a second module by encryption based on an original random code and original data; generating, by the first module a second signature by encryption based on the first random code and a checksum of the first data; and generating, by the first module, a first response to the first packet upon determining whether the second signature matches the first signature.

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.

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.

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.

A system and method are disclosed for providing an averaging of models for federated learning and blind learning systems. The method includes selecting, at a server, a generator g and a number p, transmitting, to at least two n client devices, the generator g and the number p, receiving, from each client device i of the at least two client devices, a respective value k.sub.i=g.sup.ri mod p and transmitting the set of respective values k.sub.i to each client device i of the at least two client devices where respective added group of shares are generated on each client device i. The method includes receiving each respective added group of shares from each client device i of the at least two client devices and adding all the respective added group of shares to make a global sum of shares and dividing the global sum of shares by n.

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.

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.