Real-time predictions based on machine learning models

    公开(公告)号:US12106199B2

    公开(公告)日:2024-10-01

    申请号:US18304284

    申请日:2023-04-20

    CPC classification number: G06N20/20 G06N7/01

    Abstract: An online system performs predictions for real-time tasks and near real-time tasks based on available network bandwidth. A client device receives a regression based machine learning model. Responsive to receiving a task, the client device determines an available network bandwidth for the client device. If the available network bandwidth is below a threshold, the client device uses the regression based machine learning model to perform the task. If the client device determines that the network bandwidth is above the threshold, the client device extracts features of the task, serializes the extracted features, and transmits the serialized features to an online system, causing the online system to use a different machine learning model to perform the task based on the serialized features.

    MAINTAINING SERVICE AVAILABILITY
    3.
    发明公开

    公开(公告)号:US20240195908A1

    公开(公告)日:2024-06-13

    申请号:US18080068

    申请日:2022-12-13

    CPC classification number: H04M3/2209 G06F8/31

    Abstract: Systems, devices, and techniques are disclosed for maintaining service availability. Files including code written using a Domain Specific Language (DSL) for network security may be received. A knowledge graph including connections between services may be generated from the code written using the DSL in the files. A service that will have an availability issue may be determined based on the connections between services in the knowledge graph. The service that will have the availability issue may be replicated. The replication of the service that will have the availability issue may occur before the service has the availability issue.

    REAL-TIME PREDICTIONS BASED ON MACHINE LEARNING MODELS

    公开(公告)号:US20230259831A1

    公开(公告)日:2023-08-17

    申请号:US18304284

    申请日:2023-04-20

    CPC classification number: G06N20/20 G06N7/01

    Abstract: An online system performs predictions for real-time tasks and near real-time tasks based on available network bandwidth. A client device receives a regression based machine learning model. Responsive to receiving a task, the client device determines an available network bandwidth for the client device. If the available network bandwidth is below a threshold, the client device uses the regression based machine learning model to perform the task. If the client device determines that the network bandwidth is above the threshold, the client device extracts features of the task, serializes the extracted features, and transmits the serialized features to an online system, causing the online system to use a different machine learning model to perform the task based on the serialized features.

    MULTI-FACTOR NETWORK SEGMENTATION

    公开(公告)号:US20250039155A1

    公开(公告)日:2025-01-30

    申请号:US18457557

    申请日:2023-08-29

    Abstract: Implementation(s) for multi-factor network segmentation are described. A plurality of packets at a higher layer of a network stack is processed, where at least one packet of the plurality of packets was previously determined, as part of processing the at least one packet at lower layers of the network stack, to be authorized to be processed by the higher layer. Specifically, responsive to successful authentication of a cryptographic certificate received during the handshake process, a second service is identified from the cryptographic certificate. It is determined, based on a security policy, that the second service is authorized to access the first service. Responsive to the determination, a configuration is caused such that packets sent using the source address are now authorized to be processed by the higher layer.

    MONITORING AND CONTROL OF NETWORK TRAFFIC IN A CLOUD SERVER ENVIRONMENT

    公开(公告)号:US20240372880A1

    公开(公告)日:2024-11-07

    申请号:US18143197

    申请日:2023-05-04

    Abstract: A computer-implemented method for monitoring and control of a network traffic in a cloud server environment is disclosed. The method includes receiving network traffic at a cloud service account that includes a corresponding local security enforcement module configured to enforce security policies for data processed by the cloud service account and forwarding a part of the network traffic from the cloud service account to a centralized security monitoring hub that includes a hardware-based security component. The method also includes detecting, by the hardware-based security component, offending traffic that includes traffic from an unwanted source or with malicious content. The method further includes sending a notification of the offending traffic to the localized security enforcement module, by the centralized security monitoring hub, and responsive to the notification, implementing a security enforcement strategy in the cloud service account based on the security policy, by the corresponding localized security enforcement module.

    Maintaining service availability
    7.
    发明授权

    公开(公告)号:US12256039B2

    公开(公告)日:2025-03-18

    申请号:US18080068

    申请日:2022-12-13

    Abstract: Systems, devices, and techniques are disclosed for maintaining service availability. Files including code written using a Domain Specific Language (DSL) for network security may be received. A knowledge graph including connections between services may be generated from the code written using the DSL in the files. A service that will have an availability issue may be determined based on the connections between services in the knowledge graph. The service that will have the availability issue may be replicated. The replication of the service that will have the availability issue may occur before the service has the availability issue.

    SELF HEALING NETWORK SECURITY POLICY MANAGEMENT

    公开(公告)号:US20240314175A1

    公开(公告)日:2024-09-19

    申请号:US18183490

    申请日:2023-03-14

    CPC classification number: H04L63/205 H04L63/1425

    Abstract: In some embodiments, a method determines a first functional domain that includes a group of security policies that have been copied from a second functional domain. Network flow data is queried to determine network traffic that is associated with a security policy in the group of security policies in the first functional domain. The method analyzes utilization of the security policy based on the network traffic. Based on the analyzing, a recommendation is generated to change the security policy in the first functional domain.

    SYSTEMS AND METHODS OF APPLICATION LAYER PACKET INSPECTION

    公开(公告)号:US20240259186A1

    公开(公告)日:2024-08-01

    申请号:US18101681

    申请日:2023-01-26

    CPC classification number: H04L9/0825 H04L9/3268

    Abstract: Systems and methods are provided for requesting, at a service configured on a server, a public key infrastructure (PKI) generated certificate using a PKI agent, where the PKI agent stores a private key and the generated certificate in a key management service (KMS). An application layer security controller communicatively coupled to the server registers the service to enable the application layer to inspect packets. The PKI agent transmits version information for the certificates to the application layer security controller, and the PKI agent updates the certificates and keys in the KMS. The service and an application layer datapath component change the routing of packets using an overlay network and inspect at least one of the packets. The application layer datapath component decapsulates at least one packet by using the private keys and certificates retrieved from the KMS, and performs application inspection of the decapsulated packet.

Patent Agency Ranking