International Business Machines Corporation

Kanthi K Sarpatwar

Roman Vaculin

Karthikeyan Shanmugam

Venkata Sitaramagiridharganesh Ganapavarapu

Sharathchandra UmapathiRao Pankanti

Nalini Kanta Ratha

Joel Leonard Wolf

Karthik Nandakumar

Robert Saccone

James Thomas Rayfield

Kirsten Weale Hildrum

Rohit Wagle

Zubair Nabi

Viswanath Nagarajan

Ashish Jagmohan

Michele M Franceschini

Ehud Aharoni

Omri Soceanu

Peter Daniel Kirchner

Saket Sathe

Krzysztof P Onak

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

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

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

Aspects of the present disclosure describe techniques for detecting anomalous data in an encrypted data set. An example method generally includes receiving a data set of encrypted data points. A tree data structure having a number of levels is generated for the data set. Each level of the tree data structure generally corresponds to a feature of the encrypted plurality of features, and each node in the tree data structure at a given level represents a probability distribution of a likelihood that each data point is less than or greater than a split value determined for a given feature. An encrypted data point is received for analysis, and anomaly score is calculated based on a probability identified for each of the plurality of encrypted features. Based on determining that the calculated anomaly score exceeds a threshold value, the encrypted data point is identified as potentially anomalous.

Efficient unsupervised anomaly detection on homomorphically encrypted data

A method of scheduling assignment of resources to a plurality of applications includes: determining shares of the resources assigned to each application during a first period; determining shares of the resources assigned to each application during a second period that occurs after the first period; determining an imbalance value for each application that is based on a sum of the shares assigned to the corresponding application over both periods; and considering requests of the applications for resources in an order that depends on a result of comparing the imbalance values of the applications.

Multi-platform scheduler for permanent and transient applications

Methods, systems, and computer program products for cross-platform scheduling with fairness and platform-specific optimization are provided herein. A method includes determining dimensions of a set of containers in which multiple tasks associated with a request are to be executed; assigning each of the containers to a processing node on one of multiple platforms based on the dimensions of the given container, and to a platform owner selected from the multiple platforms based on a comparison of resource requirements of each of the multiple platforms and the dimensions of the given container; and generating container assignments across the set of containers by incorporating the assigned node of each container in the set of containers, the assigned platform owner of each container in the set of containers, one or more scheduling requirements of each of the platforms, one or more utilization objectives, and enforcing a sharing guarantee of each of the platforms.

Growing community of inventors

Greenbelt, MD, United States of America

Kanthi K Sarpatwar