Abstract: A low bandwidth homomorphic encryption (HE) key generation method, a homomorphic encryption (HE) system, and a computer program product. One embodiment of the method comprises generating, at a principal instance of an organization unit, a principal HE key set; generating a department HE key set for each of a plurality of departments in the organization unit; transmitting a principal public key, a principal evaluation key, and a plurality of principal rotation keys to a data processor; transmitting at least one department public key, and department key switching keys to the data processor; and transmitting an encrypted data file to be processed at least in part using a department rotation key generated at the data processor.

Abstract: An example system includes a processor to split a graph of operations on tensors into even and odd vertical layers. In response to detecting even-even or odd-odd connections, the processor can fill the even-even or odd-odd connections using a reshape operation. The processor can also initialize outputs on a same layer type with a random packing data structure shape from a first group. The processor can then execute a breadth-first search backward based on a minimum number of shapes per layer.

Abstract: An example system includes a processor to receive a ciphertext including an encrypted packed plaintext. The processor can, in response to detecting that a reshape is to be executed for a data structure including the packed ciphertext, identify a target shape for the data structure and execute the reshape based on the identified target shape. The reshape is executed using multiplication by an identity element. The processor can then execute a homomorphic computation using the reshaped data structure.

Abstract: A computer-implemented method comprising: receiving a Boolean circuit embodied in a digital file and input variables associated with the Boolean circuit; analyzing a structure of the Boolean circuit to identify a pattern of Boolean operations comprising one or more chains of XOR operations over groups of four of the input variables; automatically evaluating each of the one or more chains of XOR operations over the groups of four input variables, using a defined logical gate XORT which replaces at least some required multiplication operations with complex conjugate operations; and automatically calculating any identified AND operations performed on adjacent XORed pairs in the Boolean circuit, using defined pseudo logical gates ANDP and XORP.

Abstract: Mechanisms are provided for fully homomorphic encryption enabled graph embedding. An encrypted graph data structure, having encrypted entities and predicates, is received and, for each encrypted entity, a corresponding set of entity ciphertexts is generated based on an initial embedding of entity features. For each encrypted predicate, a corresponding predicate ciphertext is generated based on an initial embedding of predicate features. A machine learning process is iteratively executed, on the sets of entity ciphertexts and the predicate ciphertexts, to update embeddings of the entity features of the encrypted entities and update embeddings of predicate features of the encrypted predicates, to generate a computer model for embedding entities and predicates. A final embedding is output based on the updated embeddings of the entity features and predicate features of the computer model.

Abstract: A method, apparatus and computer program product for privacy-preserving homomorphic inferencing using one-hot data representations. In this approach, a client interacting with a cloud-based server submits one-hot maps of a Chinese Remainder Theorem (CRT)-based representation of an data element, and the server expands these maps in an online phase to obtain a full one-hot map for the element. After the server obtains the full one-hot map, it performs an operation, e.g., a comparison operation associated with inferencing on a decision tree, on the one-hot map under homomorphic encryption, and in response generates a result. The result is provided back to the client.

Abstract: An example system includes a processor to train and stabilize a machine learning model using public data. The processor can fine-tune the machine learning model using anonymized private data. The processor can fine-tune the machine learning model using encrypted private data.

Abstract: A method, a neural network, and a computer program product are provided that optimize training of neural networks using homomorphic encrypted elements and dropout algorithms for regularization. The method includes receiving, via an input to the neural network, a training dataset containing samples that are encrypted using homomorphic encryption. The method also includes determining a packing formation and selecting a dropout technique during training of the neural network based on the packing technique. The method further includes starting with a first packing formation from the training dataset, inputting the first packing formation in an iterative or recursive manner into the neural network using the selected dropout technique, with a next packing formation from the training dataset acting as an initial input that is applied to the neural network for a next iteration, until a stopping metric is produced by the neural network.

Abstract: An embodiment includes performing a dedicated training process on a non-polynomial neural network resulting in a trained polynomial neural network, where the training process includes performing a plurality of training iterations on the neural network, and performing, between the training iterations, loss processing that (i) minimizes a loss of the neural network and (ii) reduces a range of values to a non-polynomial layer (NPL) of the neural network. The embodiment estimates a range of input values to the NPL of the thus trained neural network. The embodiment forms a replacement layer for the NPL, where the replacement layer comprises a polynomial approximation of an operation performed by the NPL. The embodiment also generates a revised neural network by replacing the NPL of the trained neural network with the replacement layer.

Abstract: A skip-connections analysis method, system, and computer program product for accelerating neural networks by removing skip-connections and efficient skip-connection realization.

Abstract: An example system includes a processor to receive a non-homomorphic encryption (HE)-friendly analytics model including a non-polynomial element. The processor is to train a substitution model in which the non-polynomial element of the non-homomorphic encryption (HE)-friendly analytics model is replaced with a sub-network including a polynomial replacement element.

Abstract: An example system includes a processor to mask a ciphertext using four random elements to generate masked ciphertexts. The processor can send the masked ciphertexts to a server device. The processor can receive masked plaintexts from the server device. The processor can unmask the masked plaintexts using the four random elements to generate unmasked plaintexts.

Abstract: A computer-implemented method comprising: receiving, as input, a ciphertext x representing a computational result of an approximated fully-homomorphic encryption (FHE) scheme, wherein ciphertext x comprises an underlying number m and an accumulated computational error e; iteratively, (i) performing a bit extraction operation to extract a current most significant bit (MSB) x? of ciphertext x, (ii) calculating accuracy parameters ?,? associated with x?; (iii) applying a step function to the extracted MSB x?, based, at least in part, on the calculated accuracy parameters ?,?, to reduce or remove the accumulated computational error e and to return a clean MSB b, and (iv) repeating steps (i)-(iii) for all bits included in the underlying number m; and reconstructing and outputting, from all of the returned clean MSBs b, the number m.

Abstract: An example system includes a processor to receive a circuit with a number of Boolean variables to be simulated over real numbers. The processor can encode the circuit using a negation-based encoding in response to detecting a chain of AND operations in the circuit. The processor can also execute the AND operations in the encoded circuit by summing negated variables. The processor can further reduce positive integers in results of the summed negated variables to a value of one. The processor can also further negate the results with reduced positive integers to generate decoded results of the AND operations.

Abstract: A trained neural network is partitioned into a client-side portion and a server-side portion, the client-side portion comprising a first set of layers of the trained neural network, the server-side portion comprising a second set of layers of the trained neural network, the trained neural network trained using a first set of training data. From a homomorphically encrypted intermediate result input to the server-side portion, a homomorphically encrypted output of the trained neural network is computed, the homomorphically encrypted intermediate result comprising a homomorphically encrypted output computed by the client-side portion.

Abstract: Systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to federated training and inferencing. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a modeling component that trains an inferential model using data from a plurality of parties and comprising horizontally partitioned data and vertically partitioned data, wherein the modeling component employs a random decision tree comprising the data to train the inferential model, and an inference component that responds to a query, employing the inferential model, by generating an inference, wherein first party private data, of the data, originating from a first passive party of the plurality of parties, is not directly shared with other passive parties of the plurality of parties to generate the inference.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process for privacy-enhanced machine learning and inference. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a processing component that generates an access rule that modifies access to first data of a graph database, wherein the first data comprises first party information identified as private, a sampling component that executes a random walk for sampling a first graph of the graph database while employing the access rule, wherein the first graph comprises the first data, and an inference component that, based on the sampling, generates a prediction in response to a query, wherein the inference component avoids directly exposing the first party information in the prediction.

Abstract: A technique to remotely identify potential compromise of a service provider that performs homomorphic inferencing on a model. For a set of real data samples on which the inferencing is to take place, at least first and second permutations of a set of trigger samples are generated. Every set of samples (both trigger and real samples) are then sent for homomorphic inferencing on the model at least twice, and in a secret permutated way. To improve performance, a permutation is packaged with the real data samples prior to encryption using a general purpose data structure, a tile tensor, that allows users to store multi-dimensional arrays (tensors) of arbitrary shapes and sizes. In response to receiving one or more results from the HE-based model inferencing, a determination is made whether the service provider is compromised. Upon a determination that the service provider is compromised, a given mitigation action is taken.

Abstract: A computer-implemented method comprising: generating, from a key-seed associated with a user, a set of homomorphic encryption (HE) keys associated with an HE scheme; receiving, from a key management system (KMS) associated with said HE scheme, an encrypted version of said key-seed; storing said encrypted version of said key-seed, and said set of HE keys, in an untrusted storage location; and at a decryption stage, decrypting an encrypted computation result generated using said HE scheme, by: (i) recalling, from said untrusted storage location, said encrypted version of said key-seed, (ii) providing said encrypted version of said key-seed to said KMS, to obtain a decrypted version of said key-seed s associated with said user, (iii) generating, from said received decrypted version of said key-seed, a secret HE key associated with said HE scheme, and (iv) using said secret HE key to decrypt said encrypted computation result.

Abstract: Mechanisms are provided for performing a tournament selection process of a computer function. A request is received to execute the computer function on an input vector data structure, where a result of the computer function is provided by executing the tournament selection process. The input vector data structure is received, comprising a plurality of values where each value corresponds to a vector slot. An index vector data structure is received that comprises indices of the vector slots of the input vector. Iteration(s) of the tournament selection process are executed to identify a value in the input vector satisfying a criterion of the computer function. An operation is performed on the index vector data structure to generate an indicator vector data structure that uniquely identifies a slot in the input vector data structure that is a result of the computer function being executed on the input vector data structure.