Abstract: Devices, systems, methods, and processes for dynamic power management in network devices are described herein. Power consumption in network devices may fluctuate due to varying load conditions, leading to inefficiency if all power supply units (PSUs) in these network devices remain active all the time. To address this, a network device is provided with a power management logic that dynamically tunes a count of active PSUs in the network device based on a load demand handled by various PSUs in the network device. The power management logic may receive, from the PSUs, one or more load status signals indicating the load demand handled by the PSUs. Based on the one or more load status signals, the power management logic may determine whether to increase or decrease the count of active PSUs. Dynamically adjusting the count of active PSUs may enhance energy efficiency, reduce costs, and promote sustainability.

Abstract: The present technology automates the process of collecting and using data from IoT devices to improve IoT security and management while limiting the manual entry requirements of conventional IoT platforms. The technology receives data from IoT devices and determines behavioral characterizations of the IoT devices based on the data. The technology then uses a generative model to create a file representative of the behavioral characterizations of the IoT device, and uses that file to represent new IoT devices with similar attributes to those represented by the file. In doing so, the technology can improve security by, for example, creating a MUD file representative of a new IoT device with no associated MUD file. The technology can also create a file representative of the IoT device to improve onboarding of an IoT device in, for example, an IoT operations dashboard.

Abstract: A method comprises: at an access point configured to communicate wirelessly with wireless stations: transmitting, to the wireless stations, a first multi-user trigger frame that identifies the wireless stations and allocates, to the wireless stations, resource units in which the wireless stations are to transmit data; and responsive to transmitting the first multi-user trigger frame, receiving, from the wireless stations, an uplink multi-user data frame that includes uplink data segments concurrently transmitted in the resource units by at least some of the wireless stations.

Abstract: Systems, methods, and computer-readable media are provided for detecting grey failures on a network. An example method can include receiving, by a network controller, event data for a network node, generating, by the network controller, a first metric and a second metric based on the event data, determining, by the network controller, a first pattern of growth of the first metric and a second pattern of growth of the second metric over a sliding window, determining, by the network controller, a correlation across the first metric and the second metric based on the first pattern and the second pattern, and determining, by the network controller, a grey failure of the network node based on the correlation.

Abstract: Proposed herein at techniques for scalable network traffic steering in a multi-tenant network. In one aspect, a method includes receiving, at an ingress of a multi-tenant network, a data packet, the data packet including a Virtual Network Identifier (VNI) identifying a corresponding tenant for the data packet in the multi-tenant network, and determining, at the ingress, a corresponding cluster of routers for processing the data packet based on the VNI, wherein the corresponding cluster of routers is one of a plurality of clusters of routers in the multi-tenant network. The method further includes forwarding the data packet to a router in the corresponding cluster of routers for processing.

Abstract: In one implementation, a device captures behavioral snapshots of a piece of executable code. The device generates a prompt based on the behavioral snapshots. The device generates a malware signature for the piece of executable code in part by inputting the prompt into a generative model. The device provides the malware signature for use to detect malware.

Abstract: In one embodiment, an access policy enforcement service receives a user authentication request from an end-user device. The access policy enforcement service identifies a telemetry collection intent from the user authentication request. The access policy enforcement service determines a monitoring policy based on the telemetry collection intent identified from the user authentication request. The access policy enforcement service configures, according to the monitoring policy, one or more telemetry collection agents to collect telemetry for traffic associated with the end-user device.

Abstract: The present disclosure provides techniques for transport mode selection based on MAPC deployment. A network device receives information from one or more other network devices within a CG, where the CG is configured to operate using a MAPC mode, and the information indicates a support of acting as a transport node over wired connections and a MAPC transport role within the CG for each of the other network devices. The network device estimates a wired path between the network device and at least one of the other network device, and determines transit times required for communication over the wired paths and transit times required for communication over wireless paths. Considering the transit times for the wired and wireless paths and the MAPC mode, the network device selects a transport mode, communicates the transport mode to the other network devices, and performs a network coordination operation using the transport mode.

Abstract: In one implementation, a device receives relevancy parameters from a user interface indicative of how relevant different portions of a text document are to a user. The device segments the text document into segments based on the relevancy parameters. The device generates a summary of the text document using the segments. The device provides, to the user interface, the summary of the text document and an indication of how much each of the segments contributed to the summary.

Abstract: In one embodiment, a method is disclosed comprising: monitoring, by a device and during a video conferencing session in a video conferencing area, audio quality of audio collected from a subject participating in the video conferencing session; detecting, by the device and based on the audio quality, an audio quality issue for the audio collected from the subject; generating, by the device, an orientation instruction predicted to mitigate the audio quality issue based on an audio quality visualization map generated from historical audio quality data in the video conferencing area; and providing, by the device and during the video conferencing session, the orientation instruction to the subject.

Abstract: A method to counter vulnerabilities associated with user equipment in operating via a 5G core architecture. The method includes monitoring a session between a user equipment and an endpoint, obtaining a vulnerability score for a vulnerability affecting the user equipment, selecting, based on the vulnerability score, a selected user plane function and a security service, accessible via the selected user plane function, to counter the vulnerability affecting the user equipment, and causing a packet flow of the session to be steered to the security service via the selected user plane function.

Abstract: A method, computer system, and computer program product are provided for analyzing software applications for risk. Data is obtained indicating one or more components of an application and historical data relating to one or more previous versions of the application. The historical data is analyzed to identify one or more vulnerabilities present in the one or more previous versions of the application. A software bill of materials is generated for the application based on the one or more components of the application, wherein the software bill of materials includes risk metadata descriptive of the one or more vulnerabilities of the application. The risk metadata associated with the software bill of materials is analyzed to determine a risk score for the application.

Abstract: A method of managing communication over a quantum channel. The method includes generating a first set of quantum channel codes configured to encode a message to obtain a quantum encoded message, supplying the first set of quantum channel codes to an encoder, generating a second set of quantum channel codes configured to decode the quantum encoded message, and supplying the second set of quantum channel codes to a decoder that is configured to operate with encoder across a channel, wherein the first set of quantum channel codes and the second set of quantum channel codes are derived using a machine learning model.

Abstract: Described herein is a system and method for sensor data device registration. A server receives from a client device, a device identifier associated with a sensor data device. Responsive to determining that the sensor data device is not linked to a respective dashboard, the server transmits to the client device, an indication that the sensor data device is unregistered. The server receives from the client device an indication of a dashboard to which to assign the sensor data device, and thereafter links the sensor device data to the indicated dashboard so that sensor data received from the sensor data device is presented in a user interface corresponding to the indicated dashboard.

Abstract: Disclosed are methods, controllers, and computer-readable media that explicitly label data packets and interfaces as trusted or untrusted. The data packet labeling can occur at a centralized security hub or at the enforcement site itself, i.e., at the interface to the trusted or untrusted region. The packet can be labeled with metadata associated with the packet, and that label can be carried through the transport of the packet to avoid overbroad or unnecessary security procedures. Further, a network administrator can designate certain links as trusted or untrusted so that packets designated as trusted can be sent down trusted links, and untrusted traffic can be sent down untrusted links. Network resources are saved while traffic is better separated and allocated down links with trustworthiness that is congruent with that of the packet.

Abstract: In an example, a network switch is configured to natively act as a high-speed load balancer. Numerous load-balancing techniques may be used, including one that bases the traffic “bucket” on a source IP address of an incoming packet. This particular technique provides a network administrator a powerful tool for shaping network traffic. For example, by assigning certain classes of computers on the network particular IP addresses, the network administrator can ensure that the traffic is load balanced in a desirable fashion. To further increase flexibility, the network administrator may apply a bit mask to the IP address, and expose only a portion, selected from a desired octet of the address.

Abstract: In some aspects, a method for managing security policies on a network may include a policy manager receiving, from one or more security services implemented on a network, information descriptive of a security policy data and a security status of at least one network connection between a user and a service protected by the one or more security services. The policy manager may also compare the security policy data and the security status of at least one network connection to determine one or more discrepancies between an intent of the security policy data and the security status. Finally, the policy manager may present a visual representation of the security data that includes at least an indication of the one or more discrepancies.

Abstract: The disclosed technology relates to determining a period in which a non-urgent RRM update should be deferred. The method may comprise applying a first update to an existing configuration of the plurality of wireless access points in the network based on an analysis of telemetry received from the plurality of wireless access points received over a period spanning at least two busy periods. The method may further comprise applying a second update that modifies the first preferred network configuration based on an analysis of telemetry received during the first busy period. The method may further comprise applying a maintenance update to the tweaked network configuration based on telemetry received during the next busy period.

Abstract: A trust based continuous Fifth Generation (5G) network service assessment, and more specifically a trust based continuous 5G network service assessment for a user equipment to ensure an authorized user is using the user equipment may be provided. A registration request may be received by an Access and Mobility Management Function (AMF) from a User Equipment (UE). In response to the registration request, a Policy Control Function (PCF) may exchange a policy with the AMF, wherein the policy comprises instructions to perform a continuous service assessment. Next, a registration accept message may be sent to the UE, wherein the registration accept message comprises instructions for the UE to enable the continuous service assessment.

Abstract: Methods are provided for generating end-to-end solutions-based search results for multi-query search inquiry. The search results are generated using graph generative pre-trained transformers and a network knowledge base. A method involves obtaining at least one search query and inventory data that includes information about a plurality of enterprise assets and configuration of an enterprise network. The method further includes generating a contextual schema based on the inventory data. The contextual schema includes a plurality of query sub-graphs indicative of an intention of the at least one search query and generating a solution graph by performing machine learning with respect to the plurality of query sub-graphs and network domain knowledge data. The method further includes providing a response to the at least one search query based on the solution graph. The response is specific to the enterprise network.