Lenovo (singapore) Pte. Ltd.

Truist Bank

Nvidia Corporation

Other

Amy L Rose

Nathan J Peterson

John Scott Crowe

Jennifer Lee-Baron

Gary David Cudak

Bryan Lloyd Young

Andrew James Woodard

Benjemin Thomas Waine

David Stone

Joseph Aguayo

Bryan Loyd Young

Justin Tyler Dubs

Christopher Schneider

Scott Travis Leith

William Mark Connolly

Jason Aaron Matteson

Justin Michael Ringuette

Guillermo Regulez

James Christopher Loebach

Rod D Waltermann

Grigori Zaitsev

Nagananda Chumbalkar

David Perez-Feliciano

Christopher Aaron Whitesock

Albert Sauer

William Laurence Jaeger, Jr

John Edward Long, Jr

Heather Leah Cudak

Joshua Menhaz Rahman

Johannes Zimmerman

In various examples, as a user is speaking or presenting content during an online video conference, the data stream may be processed to generate a textual representation (e.g., transcript) of the audio and/or information relating to the video. The textual representation and/or video related information may then be processed to determine a context or one or more topic(s) of discussion. Based on the determined context/topic(s), a corresponding neural network(s) may be selected. Once a neural network has been selected, comments may be retrieved from a chat feature of the application and applied to the neural network. The neural network may then output data to indicate the relevance of the comments to the determined discussion topic. Based on the relevance of the comment, the comment may be allowed, prioritized, deleted, de-emphasized, or otherwise filtered in the chat feature.

Real-time video conference chat filtering using machine learning models

Apparatuses, systems, and techniques to detect abnormal behavior on clients using one or more neural networks on said clients. In at least one embodiment, use of or behavior on one or more clients is analyzed by a first neural network to detect abnormal behavior compared to a baseline of accepted behavior, and said baseline of accepted behavior is revised over time by a second neural network based on behavior observed on said one or more clients.

Behavior modeling using client-hosted neural networks

Apparatuses, systems, and techniques to accelerate training of one or more neural networks. In at least one embodiment, training values for individual nodes in a first neural network are estimated using a second neural network or other estimation technique in order to decrease time required to train the first neural network.

Accelerated training for neural network models

Account permissions and data accessibility can be modified based on level of confidence for a login attempt to the account. User activity observations corresponding to one or more login attempts to access a user account can be stored. A confidence score associated with a successful login attempt of the user account can be determined. The confidence score is based on the user activity observations. A level of access to an application with functions and data for the user account can be determined. The level of access is based on the confidence score. The level of access is associated with the functions and the data that are executable and accessible subsequent to the successful login attempt.

Modifying application function based on login attempt confidence score

Statistical analysis can be used to attempt to identify potentially malicious references, such as trap URLs. When a URL is utilized for a request, that request can be intercepted before analysis before that URL is resolved to an address. Portions of this URL, as well as the entire URL, can be compared against one or more lists of known URLs using a probabilistic matching process to determine whether there are any matches that are very close but not quite exact. Any determined match with high probability above a suspicion threshold can be flagged as being suspicious, or associated with a potentially malicious site. An action can then be taken, such as to block that URL or prompt a user for confirmation of intent.

Detecting malformed resource references

Systems and methods are presented for reliable transmission of time-sensitive data. In particular, various embodiments provide for the generation of compressed sequential data, where individual instances of a sequence represent differentials from prior instances in that sequence. In order to reduce an amount of data that needs to be transmitted, instances of data (such as individual video frames) can be provided using a prior video frame as a reference, sending only data for those pixel locations where the pixel value differs from the reference frame. A reference frame can include a previously-received and successfully-decoded frame, in order to minimize the impact of dropped, incomplete, or corrupted frames. In order to further reduce data transmission requirements, a reference frame can be selected which is determined to be optimal for the current frame, such as may represent a least amount of data to be transmitted for a given frame.

Video compression techniques for reliable transmission

In various examples, communications having insecure protocols are dynamically hardened. For example, communications that are formatted in an outdated or otherwise insecure version of a protocol (e.g., sent by a device aged out of a service window) may be isolated within a network, converted to an updated protocol format, or any combination thereof. These systems and methods may be implemented on a general purpose network device (e.g., a hub of a Local Area Network (LAN)).

Dynamically hardening communications having insecure protocols

A method can include intercepting, by an interceptor positioned between a transfer system and a transfer settlement system, a transaction prior to the transaction being provided to the transfer settlement system. The method can include confirming that data from the transaction matches information in an immutable ledger to which parameters of the transaction have been provided by a notary system that confirms the parameters of the transaction and applies a signature using a private key to the transaction in response to confirming the parameters. The method can include, in response to confirming that the data matches the information, providing the transaction for settlement by the transfer settlement system.

In-line verification of transactions

Identification of an electronic communication containing specific information is provided. Content of the electronic communication may be evaluated by a machine-learning model, and based on an evaluation of the content, it may be determined that the electronic communication contains the specific information. The electronic communication may be tagged with tag information indicating that the electronic communication contains the specific information, and transmission of the electronic communication may be blocked based on the tag information.

Classifying types of sensitive events for data loss prevention

Annotations can be correlated to components of a document image so that the annotations track movements of the document image. A transparent overlay is generated to include the annotations and is linked to various components of the document image. Movement of the underlying document image is tracked and then adjustments in components positions are applied to associated annotations to maintain a contextual relationship between the annotations and the components of the document image.

Context aware annotations for collaborative applications

Targeted lockdown of a computer system for an identified vulnerability is provided. The targeted lockdown includes configuring a vulnerability lockdown module implemented on a computer system to perform targeted actions to change a configuration of the computer system. The targeted actions may be configured based at least in part on a type of data stored on the computer system and a potential severity of an impact on the computer system if the vulnerability is exploited. The vulnerability lockdown module may implement a vulnerability lockdown mode by causing the computer system to perform the targeted actions to change the configuration of the computer system by restricting functionality of portions of the computer system affected by the identified vulnerability. The targeted actions performed by the computer system may include altering a way in which a user interacts with the computer system.

Computer system vulnerability lockdown mode

A transaction system can include a computing device with a communication port, a processor device, and a non-transitory computer-readable storage memory. The communication port can communicate data with other computing devices. The non-transitory computer-readable storage memory includes code that is executable by the processor device to perform operations. The operations include receiving parameters of a transfer, verifying the transfer using a multi-factor authentication process, in response to verifying the transfer, using a private key to countersign the transfer and return, via the communications port, a signed transfer package for execution of the transfer, and providing, via the communications port, the parameters of the transfer and countersign data to an immutable ledger.

Growing community of inventors

Chapel, NC, United States of America

Amy L Rose