Machine learning fraud resiliency using perceptual descriptors

    公开(公告)号:US12229254B2

    公开(公告)日:2025-02-18

    申请号:US17560943

    申请日:2021-12-23

    Abstract: Machine learning fraud resiliency using perceptual descriptors is described. An example of a computer-readable storage medium includes instructions for accessing multiple examples in a training dataset for a classifier system; calculating one or more perceptual hashes for each of the examples; generating clusters of perceptual hashes for the multiple examples based on the calculation of the one or more perceptual hashes for each of the plurality of examples; obtaining an inference sample for classification by the classifier system; generating a first classification result for the inference sample utilizing a neural network classifier and generating a second classification result utilizing the generated clusters of perceptual hashes; comparing the first classification result with the second classification result; and, upon a determination that the first classification result does not match the second classification result, determining a suspicion of an adversarial attack.

    Method, system and apparatus for protecting access tokens created by multifactor authentication

    公开(公告)号:US12081538B2

    公开(公告)日:2024-09-03

    申请号:US17855648

    申请日:2022-06-30

    CPC classification number: H04L63/083 H04L63/0428 H04L63/18 H04L2463/082

    Abstract: The disclosure generally relates to method, system and apparatus for multifactor authentication exchange using out of band communication to authenticate a user while defending against the man in the middle attack. In an exemplary method, the disclosed principles provide a multifactor authentication (MFA) exchange, which includes: receiving an authentication request through in-band communication from a first device associated with a user to authenticate the user, the authentication request including a first authentication factor to identify the user; generating a second authentication factor, the second authentication factor further comprising an authorization token; generating an encryption key to encrypt the authorization token and a redirect Uniform Resource Locator (URL) address; and communicating the second authentication factor, the encryption key and the redirect URL address to a second device associated with the user.

    METHOD, SYSTEM AND APPARATUS FOR PROTECTING ACCESS TOKENS CREATED BY MULTIFACTOR AUTHENTICATION

    公开(公告)号:US20240007456A1

    公开(公告)日:2024-01-04

    申请号:US17855648

    申请日:2022-06-30

    CPC classification number: H04L63/083 H04L63/0428 H04L2463/082

    Abstract: The disclosure generally relates to method, system and apparatus for multifactor authentication exchange using out of band communication to authenticate a user while defending against the man in the middle attack. In an exemplary method, the disclosed principles provide a multifactor authentication (MFA) exchange, which includes: receiving an authentication request through in-band communication from a first device associated with a user to authenticate the user, the authentication request including a first authentication factor to identify the user; generating a second authentication factor, the second authentication factor further comprising an authorization token; generating an encryption key to encrypt the authorization token and a redirect Uniform Resource Locator (URL) address; and communicating the second authentication factor, the encryption key and the redirect URL address to a second device associated with the user.

    Supervised online identity
    35.
    发明授权

    公开(公告)号:US11611561B2

    公开(公告)日:2023-03-21

    申请号:US16913557

    申请日:2020-06-26

    Abstract: Technologies to facilitate supervision of an online identify include a gateway server to facilitate and monitor access to an online service by a user of a “child” client computer device. The gateway server may include an identity manager to receive a request for access to the online service from the client computing device, retrieve access information to the online service, and facilitate access to the online service for the client computing device using the access information. The access information is kept confidential from the user. The gateway server may also include an activity monitor module to control activity between the client computing device and the online service based on the set of policy rules of a policy database. The gateway server may transmit notifications of such activity to a “parental” client computing device for review and/or approval, which also may be used to update the policy database.

    MECHANISM FOR POISON DETECTION IN A FEDERATED LEARNING SYSTEM

    公开(公告)号:US20220114500A1

    公开(公告)日:2022-04-14

    申请号:US17558744

    申请日:2021-12-22

    Abstract: An apparatus is disclosed. The apparatus comprises one or more processors to receive trained model update data from each of a plurality of collaborators, execute an auxiliary machine learning model to the trained model update data to generate a risk score for trained model update data associated with each collaborator, apply one or more policies based on the risk scores to generate adjusted trained model update data associated with each collaborator.

    MACHINE LEARNING FRAUD RESILIENCY USING PERCEPTUAL DESCRIPTORS

    公开(公告)号:US20220114255A1

    公开(公告)日:2022-04-14

    申请号:US17560943

    申请日:2021-12-23

    Abstract: Machine learning fraud resiliency using perceptual descriptors is described. An example of a computer-readable storage medium includes instructions for accessing multiple examples in a training dataset for a classifier system; calculating one or more perceptual hashes for each of the examples; generating clusters of perceptual hashes for the multiple examples based on the calculation of the one or more perceptual hashes for each of the plurality of examples; obtaining an inference sample for classification by the classifier system; generating a first classification result for the inference sample utilizing a neural network classifier and generating a second classification result utilizing the generated clusters of perceptual hashes; comparing the first classification result with the second classification result; and, upon a determination that the first classification result does not match the second classification result, determining a suspicion of an adversarial attack.

    Technologies for managing a treatment program using smart pills

    公开(公告)号:US11135169B2

    公开(公告)日:2021-10-05

    申请号:US14998209

    申请日:2015-12-26

    Abstract: Technologies for managing a treatment program include a treatment management server, smart pills, and patient computing devices. The treatment management server is configured to generate treatment data usable by the smart pills to control a release of one or more drugs in patients. The treatment management server is also configured to transmit the treatment data to the smart pills, obtain physiological data associated with the patients, identify a preferred physiological response among the patients based on the physiological data, and identify the treatment data associated with the preferred physiological response. The smart pills are configured to obtain the treatment data, release one or more drugs into the patients based on the treatment data, sense physiological conditions in the patients, and transmit the physiological conditions to the treatment management server. The patient computing devices facilitate communication between the treatment management server and the smart pills. Other embodiments are described.

    TECHNOLOGIES FOR AUDIOVISUAL COMMUNICATION USING INTERESTINGNESS ALGORITHMS

    公开(公告)号:US20210297464A1

    公开(公告)日:2021-09-23

    申请号:US17222713

    申请日:2021-04-05

    Abstract: Technologies for audiovisual communication include an audiovisual server and a number of audiovisual client devices, including a presenter device and a number of audience devices. Each audience device captures an audiovisual stream and transmits the audiovisual stream to the audiovisual server. Each audience device also captures sensor input data such as eye tracking data or facial expression data and transmits abstracted sensor input data to the audiovisual server. The abstracted sensor input data may be based on the captured audiovisual stream. The audiovisual server determines an interestingness rating associated with each audience device based on the sensor input data, and selects one or more audiovisual streams based on the interestingness ratings. The audiovisual server transmits the selected audiovisual streams to the presenter device. The audiovisual server may update the interestingness rating algorithm based on feedback from the presenter device or the audience devices. Other embodiments are described and claimed.

    Technologies for collective authorization with hierarchical group keys

    公开(公告)号:US10790978B2

    公开(公告)日:2020-09-29

    申请号:US15271566

    申请日:2016-09-21

    Abstract: Technologies for secure collective authorization include multiple computing devices in communication over a network. A computing device may perform a join protocol with a group leader to receive a group private key that is associated with an interface implemented by the computing device. The interface may be an instance of an object model implemented by the computing device or membership of the computing device in a subsystem. The computing device receives a request for attestation to the interface, selects the group private key for the interface, and sends an attestation in response to the request. Another computing device may receive the attestation and verify the attestation with a group public key corresponding to the group private key. The group private key may be an enhanced privacy identifier (EPID) private key, and the group public key may be an EPID public key. Other embodiments are described and claimed.

Patent Agency Ranking