RUNTIME SECURITY ANALYTICS FOR SERVERLESS WORKLOADS

    公开(公告)号:US20240028704A1

    公开(公告)日:2024-01-25

    申请号:US18375149

    申请日:2023-09-29

    CPC classification number: G06F21/52 G06N20/00 G06F21/566 G06F2221/033

    Abstract: Runtime security threats are detected and analyzed for serverless functions developed for hybrid clouds or other cloud-based deployment environments. One or more serverless functions may be received and executed within a container instance executing in a controlled and monitored environment. The execution of the serverless functions is monitored, using a monitoring layer in the controlled environment to capture runtime data including container application context statistics, serverless function input and output data, and runtime parameter snapshots of the serverless functions. Execution data associated with the serverless functions may be analyzed and provided to various supervised and/or unsupervised machine-learning models configured to detect and analyze runtime security threats.

    CRYPTOGRAPHIC SECURITY AUDIT USING NETWORK SERVICE ZONE LOCKING

    公开(公告)号:US20190199753A1

    公开(公告)日:2019-06-27

    申请号:US15854879

    申请日:2017-12-27

    Abstract: In one embodiment, a service receives captured traffic flow data regarding a traffic flow sent via a network between a first device assigned to a first network zone and a second device assigned to a second network zone. The service identifies, from the captured traffic flow data, one or more cryptographic parameters of the traffic flow. The service determines whether the one or more cryptographic parameters of the traffic flow satisfy an inter-zone policy associated with the first and second network zones. The service causes performance of a mitigation action in the network when the one or more cryptographic parameters of the traffic flow do not satisfy the inter-zone policy associated with the first and second network zones.

    AUTOMATED IDENTIFICATION OF HIGHER-ORDER BEHAVIORS IN A MACHINE-LEARNING NETWORK SECURITY SYSTEM

    公开(公告)号:US20200019889A1

    公开(公告)日:2020-01-16

    申请号:US16031206

    申请日:2018-07-10

    Abstract: In one example embodiment, a server compares derived values of a plurality of machine learning features with specified values of the plurality of machine learning features according to an ontology that defines a relationship between the plurality of machine learning features and a corresponding higher-order behavior for the specified values of the plurality of machine learning features. When the derived values of the plurality of machine learning features match the specified values of the plurality of machine learning features, the server aggregates the weights of the plurality of machine learning features to produce an aggregated weight. The server assigns the aggregated weight to the higher-order behavior so as to indicate a significance of the higher-order behavior in producing the machine learning result.

    Runtime security analytics for serverless workloads

    公开(公告)号:US11809548B2

    公开(公告)日:2023-11-07

    申请号:US17077592

    申请日:2020-10-22

    CPC classification number: G06F21/52 G06F21/566 G06N20/00 G06F2221/033

    Abstract: Runtime security threats are detected and analyzed for serverless functions developed for hybrid clouds or other cloud-based deployment environments. One or more serverless functions may be received and executed within a container instance executing in a controlled and monitored environment. The execution of the serverless functions is monitored, using a monitoring layer in the controlled environment to capture runtime data including container application context statistics, serverless function input and output data, and runtime parameter snapshots of the serverless functions. Execution data associated with the serverless functions may be analyzed and provided to various supervised and/or unsupervised machine-learning models configured to detect and analyze runtime security threats.

    Automated identification of higher-order behaviors in a machine-learning network security system

    公开(公告)号:US11157834B2

    公开(公告)日:2021-10-26

    申请号:US16031206

    申请日:2018-07-10

    Abstract: In one example embodiment, a server compares derived values of a plurality of machine learning features with specified values of the plurality of machine learning features according to an ontology that defines a relationship between the plurality of machine learning features and a corresponding higher-order behavior for the specified values of the plurality of machine learning features. When the derived values of the plurality of machine learning features match the specified values of the plurality of machine learning features, the server aggregates the weights of the plurality of machine learning features to produce an aggregated weight. The server assigns the aggregated weight to the higher-order behavior so as to indicate a significance of the higher-order behavior in producing the machine learning result.

    Runtime security analytics for serverless workloads

    公开(公告)号:US12277210B2

    公开(公告)日:2025-04-15

    申请号:US18375149

    申请日:2023-09-29

    Abstract: Runtime security threats are detected and analyzed for serverless functions developed for hybrid clouds or other cloud-based deployment environments. One or more serverless functions may be received and executed within a container instance executing in a controlled and monitored environment. The execution of the serverless functions is monitored, using a monitoring layer in the controlled environment to capture runtime data including container application context statistics, serverless function input and output data, and runtime parameter snapshots of the serverless functions. Execution data associated with the serverless functions may be analyzed and provided to various supervised and/or unsupervised machine-learning models configured to detect and analyze runtime security threats.

    RUNTIME SECURITY ANALYTICS FOR SERVERLESS WORKLOADS

    公开(公告)号:US20220129540A1

    公开(公告)日:2022-04-28

    申请号:US17077592

    申请日:2020-10-22

    Abstract: Runtime security threats are detected and analyzed for serverless functions developed for hybrid clouds or other cloud-based deployment environments. One or more serverless functions may be received and executed within a container instance executing in a controlled and monitored environment. The execution of the serverless functions is monitored, using a monitoring layer in the controlled environment to capture runtime data including container application context statistics, serverless function input and output data, and runtime parameter snapshots of the serverless functions. Execution data associated with the serverless functions may be analyzed and provided to various supervised and/or unsupervised machine-learning models configured to detect and analyze runtime security threats.

    CRYPTOGRAPHIC SECURITY AUDIT USING NETWORK SERVICE ZONE LOCKING

    公开(公告)号:US20200252435A1

    公开(公告)日:2020-08-06

    申请号:US16857607

    申请日:2020-04-24

    Abstract: In one embodiment, a service receives captured traffic flow data regarding a traffic flow sent via a network between a first device assigned to a first network zone and a second device assigned to a second network zone. The service identifies, from the captured traffic flow data, one or more cryptographic parameters of the traffic flow. The service determines whether the one or more cryptographic parameters of the traffic flow satisfy an inter-zone policy associated with the first and second network zones. The service causes performance of a mitigation action in the network when the one or more cryptographic parameters of the traffic flow do not satisfy the inter-zone policy associated with the first and second network zones.

    Cryptographic security audit using network service zone locking

    公开(公告)号:US10673901B2

    公开(公告)日:2020-06-02

    申请号:US15854879

    申请日:2017-12-27

    Abstract: In one embodiment, a service receives captured traffic flow data regarding a traffic flow sent via a network between a first device assigned to a first network zone and a second device assigned to a second network zone. The service identifies, from the captured traffic flow data, one or more cryptographic parameters of the traffic flow. The service determines whether the one or more cryptographic parameters of the traffic flow satisfy an inter-zone policy associated with the first and second network zones. The service causes performance of a mitigation action in the network when the one or more cryptographic parameters of the traffic flow do not satisfy the inter-zone policy associated with the first and second network zones.

Patent Agency Ranking