公开(公告)号：US11856083B2

公开(公告)日：2023-12-26

申请号：US17569672

申请日：2022-01-06

Applicant: International Business Machines Corporation

Inventor： Ehud Aharoni ,  Omri Soceanu ,  Allon Adir ,  Gilad Ezov ,  Hayim Shaul

IPC: H04L9/00 ,  G06F9/38

CPC classification number: H04L9/008 ,  G06F9/3887

Abstract: In response to identifying that a Single Instruction, Multiple Data (SIMD) operation has been instructed to be performed or has been performed by a Fully-Homomorphic Encryption (FHE) software on one or more original ciphertexts, performing the following steps: Performing the same operation on one or more original plaintexts, respectively, that are each a decrypted version of one of the one or more original ciphertexts. Decrypting a ciphertext resulting from the operation performed on the one or more original ciphertexts. Comparing the decrypted ciphertext with a plaintext resulting from the same operation performed on the one or more original plaintexts. Based on said comparison, performing at least one of: (a) determining an amount of noise caused by the operation, (b) determining whether unencrypted data underlying the one or more original ciphertexts has become corrupt by the operation, and (c) determining correctness of an algorithm which includes the operation.

公开(公告)号：US12289393B2

公开(公告)日：2025-04-29

申请号：US17992597

申请日：2022-11-22

Applicant: International Business Machines Corporation

Inventor： Ramy Masalha ,  Ehud Aharoni ,  Nir Drucker ,  Gilad Ezov ,  Hayim Shaul ,  Omri Soceanu

IPC: H04L9/06 ,  H04L9/00

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.

公开(公告)号：US12192321B2

公开(公告)日：2025-01-07

申请号：US17875987

申请日：2022-07-28

Applicant: International Business Machines Corporation

Inventor： Runhua Xu ,  Nathalie Baracaldo Angel ,  Hayim Shaul ,  Omri Soceanu

IPC: H04L9/00 ,  G06N20/00

Abstract: A second set of data identifiers, comprising identifiers of data usable in federated model training by a second data owner, is received at a first data owner from the second data owner. An intersection set of data identifiers is determined at the first data owner. At the first data owner according to the intersection set of data identifiers, the data usable in federated model training is rearranged by the first data owner to result in a first training dataset. At the first data owner using the intersection set of data identifiers, the first training dataset, and a previous iteration of an aggregated set of model weights, a first partial set of model weights is computed. An updated aggregated set of model weights, comprising the first partial set of model weights and a second partial set of model weights from the second data owner, is received from an aggregator.

公开(公告)号：US20240275577A1

公开(公告)日：2024-08-15

申请号：US18102735

申请日：2023-01-29

Applicant: International Business Machines Corporation

Inventor： Nir Drucker ,  Guy Moshkoich ,  Tomer Pelleg ,  Hayim Shaul

IPC: H04L9/00 ,  H04L9/06

CPC classification number: H04L9/008 ,  H04L9/0618

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 α,β associated with x′; (iii) applying a step function to the extracted MSB x′, based, at least in part, on the calculated accuracy parameters α,β, 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.

公开(公告)号：US11841982B2

公开(公告)日：2023-12-12

申请号：US17505964

申请日：2021-10-20

Applicant: International Business Machines Corporation

Inventor： Hayim Shaul ,  Ehud Aharoni ,  Dov Murik ,  Omri Soceanu ,  Gilad Ezov ,  Lev Greenberg ,  Evgeny Shindin

IPC: G06F21/72 ,  H04L9/00 ,  G06F21/60 ,  G06F21/14

CPC classification number: G06F21/72 ,  G06F21/602 ,  H04L9/008 ,  G06F21/14 ,  H04L2209/125

Abstract: An example system includes a processor that can obtain a circuit describing operations of sequential secure computation code. The processor can modify the circuit based on a cost function. The processor can partition the circuit into a number of sub-circuits. The processor can assign the number of the sub-circuits to different processors for execution.

公开(公告)号：US20230297649A1

公开(公告)日：2023-09-21

申请号：US17655566

申请日：2022-03-21

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Nir Drucker ,  Ehud Aharoni ,  Hayim Shaul ,  Allon Adir ,  Lev Greenberg

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  H04L9/00

CPC classification number: G06K9/6257 ,  G06N3/08 ,  G06N3/04 ,  H04L9/008

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.

公开(公告)号：US12250293B2

公开(公告)日：2025-03-11

申请号：US17936113

申请日：2022-09-28

Applicant: International Business Machines Corporation

Inventor： Nir Drucker ,  Hayim Shaul

IPC: G09C1/00 ,  H04L9/00 ,  H04L9/06 ,  H04L9/30

Abstract: An example system includes a processor to partition an arithmetic circuit representing a homomorphically encrypted (HE) code into a number of execution blocks. The processor can generate, for each of the number of execution blocks, manifests describing access patterns for a number of different machine environments. The processor can then dynamically execute the HE code by selecting successive blocks to execute based on an access pattern calculated for the execution block corresponding to a detected current machine environment.

公开(公告)号：US20250080317A1

公开(公告)日：2025-03-06

申请号：US18242067

申请日：2023-09-05

Applicant: International Business Machines Corporation

Inventor： Allon Adir ,  Ramy Masalha ,  Ehud Aharoni ,  Hayim Shaul

IPC: H04L9/00 ,  G06F17/11

Abstract: An embodiment expands a polynomial into a plurality of products, each product in the plurality of products comprising a scaling coefficient multiplied by a sub-polynomial, each sub-polynomial comprising a sum of a plurality of addends, wherein a degree of each sub-polynomial is equal to a grouping parameter. An embodiment computes a plurality of ciphertext products, each ciphertext product equal to a ciphertext multiplied by itself a number of times, the number of times ranging from two to the grouping parameter. An embodiment computes, using the ciphertext and the plurality of ciphertext products in place of a variable of the polynomial, each of the plurality of products. An embodiment multiplies the plurality of products together.

公开(公告)号：US12130889B2

公开(公告)日：2024-10-29

申请号：US17655566

申请日：2022-03-21

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Nir Drucker ,  Ehud Aharoni ,  Hayim Shaul ,  Allon Adir ,  Lev Greenberg

IPC: G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  H04L9/00

CPC classification number: G06F18/2148 ,  G06N3/04 ,  G06N3/08 ,  H04L9/008

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.

公开(公告)号：US20240297777A1

公开(公告)日：2024-09-05

申请号：US18114682

申请日：2023-02-27

Applicant: International Business Machines Corporation

Inventor： Hayim Shaul ,  Guy Moshkowich ,  Eyal Kushnir

IPC: H04L9/00 ,  G06F16/2455

CPC classification number: H04L9/008 ,  G06F16/24564

Abstract: Mechanisms are provided for performing a fully homomorphic encryption operation. The mechanisms generate, for a data set in a backend data store, a tree data structure comprising a hierarchy of nodes and edges connecting the nodes in a parent-child relationship. In response to receiving an encrypted query from a client computing device, a search operation is executed using the tree data structure at least by executing a copy-and-recurse computing tool to identify a portion of the tree data structure to which to apply a fully homomorphic encryption (FHE) operation. The copy-and-recurse computing tool copies a subset of nodes of the tree data structure and recurses the search operation into the copied subset of nodes. The FHE operation is executed on a portion of the data set, corresponding to the identified portion of the tree data structure, to generate results of the FHE operation which are then output.