International Business Machines Corporation

Airbnb, Inc.

Roman Vaculin

Kuntal Dey

Seema Nagar

Karan Ahuja

Kanthi K Sarpatwar

Karthikeyan Shanmugam

Rong Liu

Venkata Sitaramagiridharganesh Ganapavarapu

Ashish Jagmohan

Gennaro A Cuomo

Donna N Dillenberger

Sudhanshu Shekhar Singh

Jinfeng Yi

Wei Sun

Kush Raj Varshney

James Thomas Rayfield

Elham Khabiri

Richard B Segal

Michael James Hind

Sekou Lionel Remy

Nelson Kibichii Bore

Utkarsh Dwivedi

Ravi Kiran Raman

Eleftheria K Pissadaki

Sharathchandra UmapathiRao Pankanti

Nalini Kanta Ratha

Nianjun Zhou

Karthik Nandakumar

Heena Bansal

Fenno F Heath, Iii

Stacy Fay Hobson

Matous Havlena

David T Adamo, Jr

Qi Lei

Maja Vukovic

Daniel Joseph Friedman

Chandrasekhar Narayanaswami

Michele M Franceschini

Yu Deng

Richard Harold Boivie

Hong Min

Sheng Hua Bao

Gi-Joon Nam

Ying Li

Jim Alain Laredo

Ehud Aharoni

Omri Soceanu

Frederick Y Wu

Qi Hu

Rema Ananthanarayanan

Jun-Jang Jeng

Enriquillo Valdez

Arun Paidimarri

Anil Nigam

Pavankumar Murali

Jinwook Jung

Seep Goel

Saket Sathe

Abhilash Narendra

Nigel Hinds

Hong Lin Guo

Zhiyuan Li

Kanthi Sarpatwar

Pooja Aggarwall

Chian-Rou Shieh

Zhe Shan

A method, apparatus and computer program product that provides multi-phase privacy-preserving inferencing in a high throughput data environment, e.g., to facilitate fraud prediction, detection and prevention. In one embodiment, two (2) machine learning models are used, a first model that is trained in the clear on first transaction data, and a second model that is trained in the clear but on the first transaction data, and user data. The first model is used to perform inferencing in the clear on the high throughput received data. In this manner, the first model provides a first level evaluation of whether a particular transaction might be fraudulent. If a transaction is flagged in this first phase, a second more secure inference is then carried out using the second model. The inferencing performed by the second model is done on homomorphically encrypted data. Thus, only those transactions marked by the first model are passed to the second model for secure evaluation.

Multi-phase privacy-preserving inferencing in a high volume data environment

In an approach for training machine-learning models using encrypted data, a processor receives a set of encrypted data from a client computing device. A processor trains a machine-learning model using a boosting algorithm. A processor performs a first classification on the set of encrypted data using the machine-learning model. A processor sends a first set of encrypted results of the first classification to the client computing device. A processor receives a first set of boosting updates from the client computing device. A processor applies the first set of boosting updates to the machine-learning model.

Enabling boosting protocols on encrypted data

Techniques that facilitate machine learning using multi-dimensional time series data are provided. In one example, a system includes a snapshot component and a machine learning component. The snapshot component generates a first sequence of multi-dimensional time series data and a second sequence of multi-dimensional time series data from multi-dimensional time series data associated with at least two different data types generated by a data system over a consecutive period of time. The machine learning component that analyzes the first sequence of multi-dimensional time series data and the second sequence of multi-dimensional time series data using a convolutional neural network system to predict an event associated with the multi-dimensional time series data.

Multi-dimensional time series event prediction via convolutional neural network(s)

Privacy-preserving homomorphic inferencing utilizes batch processing on encrypted data records. Each data record has a private data portion of interest against which the inferencing is carried out. Batch processing is enabled with respect to a set of encrypted data records by techniques that ensure that each encrypted data record has its associated private data portion in a unique location relative to the other data records. The set of encrypted data records are then summed to generate a single encrypted data record against which the inferencing is done. In a first embodiment, the private data portions of interest are selectively and uniquely positioned at runtime (when the inferencing is being applied). In a second embodiment, the private data portions of interest are initially positioned with the data-at-rest, preferably in an off-line process; thereafter, at runtime individual encrypted data records are processed as necessary to adjust the private data portions to unique positions prior to batching.

Efficiently batching pre-encrypted data for homomorphic inference

An example operation may include one or more of generating, by a training participant client, a plurality of transaction proposals, each of the plurality of transaction proposals corresponding to a training iteration for machine learning model training related to stochastic gradient descent, the machine learning model training comprising a plurality of training iterations, the transaction proposals comprising a gradient calculation performed by the training participant client, transferring the plurality of transaction proposals to one or more endorser nodes or peers each comprising a verify gradient smart contract, executing, by each of the endorser nodes or peers, the verify gradient smart contract; and providing endorsements corresponding to the plurality of transaction proposals to the training participation client.

Efficient verification of machine learning applications

An example operation may include one or more of generating a hashed summary including hashes of one or more of a validation data set and hashes of data points chosen in previous iterations from producer nodes, and exposing the hashed summary to a plurality of producer nodes, receiving, iteratively, a plurality of requests from the plurality of producer nodes, respectively, where each request identifies a marginal value provided by a hash of a data sample available to a producer node, selecting a request received from a producer node based on a marginal value associated with the request, retrieving hashed data of the producer node associated with the selected request, and aggregating the hashed data of the producer node with the summary of hashes generated at one or more previous iterations to produce an updated summary, and storing the updated summary via a data block of a distributed ledger.

Artificial intelligence software marketplace

An example operation may include one or more of generating a plurality of successive data points of an iterative simulation based on predefined checkpoints, each data point identifying an evolving state of the iterative simulation with respect to a previous data point among the successive data points, transmitting a blockchain request for validating state data within a first data point among the plurality of successive data points to a first subset of endorsing nodes of a blockchain network, and transmitting a blockchain request for validating state data within a second data point among the plurality of successive data points to a second subset of endorsing nodes which are mutually exclusive from the first subset of endorsing nodes of the blockchain network for parallel endorsement of the first and second data points.

Distributed platform for computation and trusted validation

An example operation may include one or more of obtaining data of a simulation, identifying checkpoints within the simulation data, generating a plurality of sequential data structures based on the identified checkpoints, where each data structure identifies an evolving state of the simulation with respect to a previous data structure among the sequential data structures, and transmitting the generated sequential data structures to nodes of a blockchain network for inclusion in one or more data blocks within a hash-linked chain of data blocks.

A method, apparatus and computer program product for homomorphic inference on a decision tree (DT) model. In lieu of HE-based inferencing on the decision tree, the inferencing instead is performed on a neural network (NN), which acts as a surrogate. To this end, the neural network is trained to learn DT decision boundaries, preferably without using the original DT model data training points. During training, a random data set is applied to the DT, and expected outputs are recorded. This random data set and the expected outputs are then used to train the neural network such that the outputs of the neural network match the outputs expected from applying the original data set to the DT. Preferably, the neural network has low depth, just a few layers. HE-based inferencing on the decision tree is done using HE inferencing on the shallow neural network. The latter is computationally-efficient and is carried without the need for bootstrapping.

Decision tree-based inference on homomorphically-encrypted data without bootstrapping

An example operation may include one or more of generating, by a plurality of training participant clients, gradient calculations for machine learning model training, each of the training participant clients comprising a training dataset, converting, by a training aggregator coupled to the plurality of training participant clients, the gradient calculations to a plurality of transaction proposals, receiving, by one or more endorser nodes or peers of a blockchain network, the plurality of transaction proposals, executing, by each of the endorser nodes or peers, a verify gradient smart contract, and providing endorsements corresponding to the plurality of transaction proposals to the training aggregator.

Aggregated machine learning verification for database

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.

Depth-constrained knowledge distillation for inference on encrypted data

An example operation may include one or more of generating, by a training participant client comprising a training dataset, a plurality of transaction proposals that each correspond to a training iteration for machine learning model training related to stochastic gradient descent, the machine learning model training comprising a plurality of training iterations, the transaction proposals comprising a gradient calculation performed by the training participant client, a batch from the private dataset, a loss function, and an original model parameter, receiving, by one or more endorser nodes of peers of a blockchain network, the plurality of transaction proposals, and evaluating each transaction proposal.

A technique for computationally-efficient privacy-preserving homomorphic inferencing against a decision tree. Inferencing is carried out by a server against encrypted data points provided by a client. Fully homomorphic computation is enabled with respect to the decision tree by intelligently configuring the tree and the real number-valued features that are applied to the tree. To that end, and to the extent the decision tree is unbalanced, the server first balances the tree. A cryptographic packing scheme is then applied to the balanced decision tree and, in particular, to one or more entries in at least one of: an encrypted feature set, and a threshold data set, that are to be used during the decision tree evaluation process. Upon receipt of an encrypted data point, homomorphic inferencing on the configured decision tree is performed using a highly-accurate approximation comparator, which implements a 'soft' membership recursive computation on real numbers, all in an oblivious manner.

Privacy-enhanced decision tree-based inference on homomorphically-encrypted data

An example operation includes one or more of computing, by a data owner node, updated gradients on a loss function based on a batch of private data and previous parameters of a machine learning model associated with a blockchain, encrypting, by the data owner node, update information, recording, by the data owner, the encrypted update information as a new transaction on the blockchain, and providing the update information for an audit.

Verification of stochastic gradient descent

Techniques for outside-in mapping for corpus pairs are provided. In one example, a computer-implemented method comprises: inputting first keywords associated with a first domain corpus; extracting a first keyword of the first keywords; inputting second keywords associated with a second domain corpus; generating an embedded representation of the first keyword via a trained model and generating an embedded representation of the second keywords via the trained model; and scoring a joint embedding affinity associated with a joint embedding. The scoring the joint embedding affinity comprises: transforming the embedded representation of the first keyword and the embedded representation of the second keywords via the trained model; determining an affinity value based on comparing the first keyword to the second keywords; and based on the affinity value, aggregating the joint embedding of the embedded representation of the first keyword and the embedded representation of the second keywords within the second domain corpus.

Joint embedding of corpus pairs for domain mapping

Growing community of inventors

Bronxville, NY, United States of America

Roman Vaculin