Intel Corporation

Mcafee, Inc.

Micah James Sheller

Ned M Smith

Jason Martin

Nathan Heldt-Sheller

Cory Cornelius

Conor Patrick Cahill

Yonghong Huang

Kevin C Wells

Sindhu Pandian

Nathaniel J Goss

Brandon Baker

Reshma Lal

Bin Xing

Victoria C Moore

Bradley William Corrion

Hannah L Scurfield

Shih-Han Wang

Somnath Chakrabarti

Abhilasha Bhargav-Spantzel

Matthew Eldon Hoekstra

Narjala Prakash Bhasker

Jeffrey Tripp

Bernard N Keany

Samir Shah

Shih-han Wang

Brad H Needham

Hormuzd M Khosravi

Michael E Kounavis

Vincent R Scarlata

Pradeep M Pappachan

Narayan Biswal

Krystof C Zmudzinski

Barnan Das

Jasmeet Chhabra

Jeffrey Sedayao

Li Chen

Dmitri Rubakha

Ramune Nagisetty

Reese Bowes

Prakash Narayana Moorthy

Anindya Sankar Paul

Patrick Noel Foley

G Anthony Reina

Antonios Papadimitriou

Brandon Edwards

Clair Bowman

Thao W Xiong

Jeffrey M Tripp

Bradley W Corrion

A method comprises receiving in a governor device, from a plurality of data owner devices, metadata for one or more datasets maintained by the plurality of data owner devices, registering the metadata for the one or more datasets with the governor device, in response to a request from an aggregator, providing at least a portion of the metadata for the one or more datasets to the aggregator, receiving, from the aggregator, a compute plan to be implemented by the plurality of data owner devices, distributing at least a portion of the compute plan to the plurality of data owner devices, in response to receiving, from the plurality of data owner devices, a verification report and a certification for an enclave, binding the enclave to a host device, and providing the compute plan to the plurality of data owner devices.

Provisioning federated computation on distributed private data

Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

Methods and apparatus for distributed use of a machine learning model

In one example an apparatus comprises a memory and a processor to create, from a first deep neural network (DNN) model, a first plurality of DNN models, generate a first set of adversarial examples that are misclassified by the first plurality of deep neural network (DNN) models, determine a first set of activation path differentials between the first plurality of adversarial examples, generate, from the first set of activation path differentials, at least one composite adversarial example which incorporates at least one intersecting critical path that is shared between at least two adversarial examples in the first set of adversarial examples, and use the at least one composite adversarial example to generate a set of inputs for a subsequent training iteration of the DNN model. Other examples may be described.

Adversarial training of neural networks using information about activation path differentials

Methods, apparatus, systems and articles of manufacture for federated training of a neural network using trusted edge devices are disclosed. An example system includes an aggregator device to aggregate model updates provided by one or more edge devices. The one or more edge devices to implement respective neural networks, and provide the model updates to the aggregator device. At least one of the edge devices to implement the neural network within a trusted execution environment.

Methods and apparatus for federated training of a neural network using trusted edge devices

Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

Techniques to detect perturbation attacks with an actor-critic framework

Various systems and methods for Internet of Things (IoT) network sensor fusion are provided herein. A system for providing sensor collaboration includes: a sensor command circuit to access first-tier sensor data from a first-tier sensor associated with a user; a risk assessment circuit to use the first-tier sensor data to determine a risk rating, the risk rating representing a potential risk to the user; a user context circuit to determine a user context from the first-tier sensor data, wherein the user context circuit and the sensor command circuit are to selectively access second-tier sensor data from a second-tier sensor based on the user context; and a rule evaluation circuit to access a rule database to identify a rule corresponding to the risk rating and user context, and execute the rule when the rule is identified.

IoT sensor fusion

In one embodiment, an apparatus includes: a bioimpedance sensor to generate bioimpedance information based on bioimpedance sample information from at least some of a plurality of electrodes to be adapted about a portion of a person; at least one biometric sensor to generate biometric information based on biometric sample information from at least some of the plurality of electrodes; at least one environmental sensor to generate environmental context data; and an integration circuit to receive the bioimpedance information, the biometric information and the environmental context data and to adjust the bioimpedance information based at least in part on a value of one or more of the biometric information and the environmental context data. Other embodiments are described and claimed.

System, apparatus and method for providing contextual data in a biometric authentication system

Various embodiments are generally directed to an apparatus, method, and other techniques to maintain user authentications with common trusted devices. If a user is in possession of a first computing device (e.g., a smartphone), an unlocked state of the first trusted device is maintained if the user is using a nearby trusted device (e.g., a computer) within a certain amount of time. If the first trusted device is in a pocket or other container, a longer span of time is granted to the user to register an on-body state.

Maintaining user authentications with common trusted devices

Various embodiments are generally directed to the provision and use of geometric location based security systems that use multiple beacons for determining a location. A beacon transmitted from an ultrasound broadcast as well as one or more different wireless broadcasts can be used to geo-locate a device and provide access controls based on the geo-location.

Multi-signal geometric location sensing for access control

Technologies for analyzing a Uniform Resource Locator (URL) include a multi-stage URL analysis system. The multi-stage URL analysis system analyzes the URL using a multi-stage analysis. In the first stage, the multi-stage URL analysis system analyzes the URL using an ensemble lexical analysis. In the second stage, the multi-stage URL analysis system analyzes the URL based on third-party detection results. In the third stage, the multi-stage URL analysis system analyzes the URL based on metadata related to the URL. The multi-stage URL analysis system advances the stages of analysis if a malicious classification score determined by each stage does not satisfy a confidence threshold. The URL may also be selected for additional rigorous analysis using selection criteria not used in by the analysis stages.

Technologies for analyzing uniform resource locators

Technologies for supporting and implementing multiple digital rights management protocols on a client device are described. In some embodiments, the technologies include a client device having an architectural enclave which may function to identify one of a plurality of digital rights management protocols for protecting digital information to be received from a content provider or a sensor. The architectural enclave select a preexisting secure information processing environment (SIPE) to process said digital information, if a preexisting SIPE supporting the DRM protocol is present on the client. If a preexisting SIPE supporting the DRM protocol is not present on the client, the architectural enclave may general a new SIPE that supports the DRM protocol on the client. Transmission of the digital information may then be directed to the selected preexisting SIPE or the new SIPE, as appropriate.

Technologies for supporting multiple digital rights management protocols on a client device

Technologies for multi-factor authentication of a user include a computing device with one or more sensors. The computing device may authenticate the user by analyzing biometric and/or environmental sensor data to determine whether to allow the user access to a computing device. To do so, the computing device may determine reliability scores based on the environment during authentication for each biometric authentication factor used to authenticate the user. Additionally, the computing device may determine a login pattern based on sensor data collected during historical authentication attempts by the user over a period of time. The computing device may apply a machine-learning classification algorithm to determine classification rules, based on the login pattern, applied by the computing device to determine whether to allow the user access to the computing device. Other embodiments are described herein and claimed.

Technologies for login pattern based multi-factor authentication

In an embodiment, a security engine of a processor includes an identity provider logic to generate a first key pair of a key pairing associating system user and a service provider that provides a web service and having a second system coupled to the system via a network, to perform a secure communication with the second system to enable the second system to verify that the identity provider logic is executing in a trusted execution environment, and responsive to the verification, to send a first key of the first key pair to the second system. This key may enable the second system to verify an assertion communicated by the identity provider logic that the user has been authenticated to the system according to a multi-factor authentication. Other embodiments are described and claimed.

Privacy enhanced key management for a web service provider using a converged security engine

Growing community of inventors

Hillsboro, OR, United States of America

Micah James Sheller