International Business Machines Corporation

Lenovo (singapore) Pte. Ltd.

Nalini Kanta Ratha

Jonathan Hudson Connell, Ii

Sharathchandra UmapathiRao Pankanti

Rudolf Maarten Bolle

Karthik Nandakumar

Lawrence Alfred Clevenger

Michael Rizzolo

Benjamin David Briggs

Leigh Anne H Clevenger

Gaurav Goswami

Shai Halevi

Noel C Codella

Sharathchandra Umapathirao Pankanti

Jonathan H Connell

Jae-Eun Park

Yu Cheng

James E Gentile

Roman Vaculin

Chitra Dorai

Karthikeyan Shanmugam

Kanthi K Sarpatwar

Fred A Maymir-Ducharme

Sharat Suresh Chikkerur

Ashish Kundu

Andrew William Senior

Robert G Farrell

Maryam Ashoori

Tsai-Yang Jea

Gaurav Aggarwal

Shelby Solomon Darnell

Jonathan Hudson Connell

Richa Singh

Mayank Vatsa

Fred A Maynir-Ducharme

Jinyu Zuo

Sunil J Noronha

Hariklia Deligianni

Komminist S Weldemariam

John Richard Smith

Thomas Guthrie Zimmerman

Sugata Ghosal

Samuel Jonathan Thomas

Michael Alan Schappert

Saritha Arunkumar

James Thomas Rayfield

James Lewis Levine

Barton Allen Smith

Lisa Marie Brown

Richard L Garwin

Apostol Ivanov Natsev

Robert S Germain

Hui Wu

Vince Siu

Chung-Ching Lin

Roberto Sicconi

Sharon L Nunes

Christos Sagonas

Raghavendra Uppinakuduru Udupa

Pawel G Musial

Gong Leiguang

Emrah Akin Sisbot

Peter W Waggett

Xi Peng

Louis J Percello

Carl E Abrams

Sarathchandra Pankanti

Sharathchandra Umpathirao Pankanti

Jordan Soet

A drug delivery device includes a capsule, a logic circuit disposed within the capsule, and an actuator connected to the logic circuit and configured to expose an interior of the capsule to an exterior of the capsule upon activation by the logic circuit.

Drug delivery device having controlled delivery and confirmation

ML model(s) are created and trained using training data from user(s) to create corresponding trained ML model(s). The training data is in FHE domains, each FHE domain corresponding to an individual one of the user(s). The trained machine learning model(s) are run to perform inferencing using other data from at least one of the user(s). The running of the ML model(s) determines results. The other data is in a corresponding FHE domain of the at least one user. Using at least the results, it is determined which of the following issues is true: the results comprise objectionable material, or at least one of the trained ML model(s) performs prohibited release of information. One or more actions are taken to take to address the issue determined to be true. Methods, apparatus, and computer program product are disclosed.

Searching over encrypted model and encrypted data using secure single-and multi-party learning based on encrypted data

An entity learning recognition method, system, and computer program product include learning (i.e., in a training phase) from at least one entity to produce augments entities such that an augmented entity is still recognizable as the original entity but differs sufficiently to produce a different feature representation of the entity to create a database for use (i.e., in an implementation phase).

Entity learning recognition

Determining lung capacity of includes capturing an audio waveform of the user performing an utterance presented to a user. A video of the user performing the utterance can be captured. The captured audio waveform and the video are analyzed for compliance. Based on the audio waveform, an indicator of respiratory function is determined. The indicator is compared with a reference indicator to determine health of the user. A machine learning model such as neural network can be trained to predict the indicator of the respiratory function based on input features comprising audio spectral and temporal characteristics of utterances. Determining the indicator or respiratory function can include running the trained machine learning model.

Multi-modal lung capacity measurement for respiratory illness prediction

An entity learning recognition method and computer program product include learning training a model based on a combination of an original entity and an augmented entity in an augmented database, where the entity includes an image that is used for a training of the model and where the training is based on a visual element portion of the image with added noise.

Securely re-encrypting homomorphically encrypted data by receiving fully homomorphically encrypted (FHE) information from a client device, training a machine learning model using the FHE information, yielding FHE ciphertexts, applying a first transform to the FHE ciphertexts, yielding obfuscated FHE ciphertexts, sending the obfuscated FHE ciphertexts to a secure device, receiving a re-encrypted version of the obfuscated FHE ciphertexts from the secure device, applying a second transform to the re-encrypted version of the obfuscated FHE ciphertexts yielding de-obfuscated re-encrypted FHE ciphertexts, determining FHE ML model parameters according to the de-obfuscated re-encrypted ciphertexts, and sending the FHE ML model parameters to the client device.

Secure re-encryption of homomorphically encrypted data

A framework is provided in which a querying agency can request (via a query entity) encrypted data through a service provider from a data owning agency that stores encrypted data. The framework uses homomorphic encryption. The data may be gallery entities, and each of the elements in the framework operate on doubly-encrypted information. The service provider compares a representation of an encrypted query entity from the querying agency and representations of encrypted gallery entities from the data owning agency, resulting in doubly-encrypted values of a metric between corresponding compared representations. The querying agency gets result(s), based on the metric, which indicate whether it is probable the service provider has data similar to or the same as query data in the query entity. The elements have to perform communication in order for the querying agency or the data owning agency to get cleartext information corresponding to the query entity.

Secure matching and identification of patterns

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

A neural network is configured to suppress an output of a mitigation node in a mitigation layer of the neural network. The neural network is pre-configured to recognize objects from inputs when operating using a processor and a memory. An actual input is sent to the neural network for object recognition, the actual input is an altered input. By suppressing the output of the mitigation node, the neural network is caused to avoid falsely recognizing an object from the actual input, where the altered input is configured to cause the neural network to falsely recognize the object from the actual input.

Mitigating false recognition of altered inputs in convolutional neural networks

Generating visual data by defining a first action into a first set of objects and corresponding first set of motions, and defining a second action into a second set of objects and corresponding second set of motions. A relationship is then determined for the second action to the first action in terms of relationships between corresponding constituent objects and motions. Objects and motions are detected from visual data of first action. Visual data is composed for the second action from the data by transforming the constituent objects and motions detected in first action based on the corresponding determined relationships.

Augmentation for visual action data

Mechanisms are provided to implement a privacy enhanced location service for determining a granularity of location information to return to a requestor computing device. The privacy enhanced location service receives, from a requestor computing device, a location query requesting location information for a subject. The privacy enhanced location service retrieves a selected subject privacy policy data structure, selected from a set of subject privacy policy data structures corresponding to the subject identified in the location query. The privacy enhanced location service applies the selected subject privacy policy data structure to location information associated with the subject to generate modified location information having a granularity of location information specified in the selected subject privacy policy data structure. The privacy enhanced location service transmits the modified location information to the requestor computing device.

Privacy enhanced location verification for improved transaction security

Mechanisms are provided to provide an improved computer tool for determining and mitigating the presence of adversarial inputs to an image classification computing model. A machine learning computer model processes input data representing a first image to generate a first classification output. A cohort of second image(s), that are visually similar to the first image, is generated based on a comparison of visual characteristics of the first image to visual characteristics of images in an image repository. A cohort-based machine learning computer model processes the cohort of second image(s) to generate a second classification output and the first classification output is compared to the second classification output to determine if the first image is an adversarial image. In response to the first image being determined to be an adversarial image, a mitigation operation by a mitigation system is initiated.

Cohort based adversarial attack detection

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

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

Growing community of inventors

Yorktown Heights, NY, United States of America

Nalini Kanta Ratha