Abstract: The present disclosure is directed towards systems and methods for detecting anomalous network traffic. Network traffic corresponding to an application executed by a server can be received. Application characteristics of the application can be identified to select an anomaly detection profile. The anomaly detection profile can be selected based on the identified application characteristics. The anomaly detection profile can include a set of detection features for the anomaly and one or more predetermined threshold values of the detection features. One or more feature values of the set of one or more detection features can be determined. An anomaly in the network traffic can be detected responsive to comparing the feature values and the predetermined threshold values of the detection features.

Abstract: Systems and methods for protection against session stealing is described. In embodiments of the present solution, a device intermediary to the client and the server may identify first properties of the client and associate the first properties with the session key. When the device receives subsequent request comprising the session key, the device matches the associated first properties with second properties of the second device that is sending the subsequent request. If there is a match, the subsequent request transmitted to the server. Otherwise, the subsequent request is rejected.

Abstract: The present disclosure is directed towards systems and methods for improving anomaly detection using injected outliers. A normalcy calculator of a device may include a set of outliers into a training dataset of data points. The normalcy calculator, using a K-means clustering algorithm applied on the training dataset, identify at least a first cluster of data points. The normalcy calculator of the device may determine a region with a center and an outer radius that covers at least a spatial extent of the first cluster of data points. The normalcy calculator may determine a first normalcy radius for the first cluster by reducing the region around the center until a point at which all artificial outliers are excluded from a region defined by the first normalcy radius. An outlier detector of the device may use the region defined by the first normalcy radius to determine whether a new data point is normal or abnormal.

Abstract: The present disclosure is directed towards systems and methods for characterizing anomalous network traffic. The system includes a device intermediary to clients and servers. The device includes a network traffic engine to receive network traffic including an anomaly. The device includes a univariate policy manager to determine whether the network traffic satisfies at least one of the rules of a univariate policy based on a respective single independent network traffic feature. The device includes a multivariate policy manager to determine, responsive to determining that the network traffic does not satisfy the rules of the univariate policy, that the network satisfies a multivariate policy including a plurality of anomaly explanation tests. The device includes an anomaly explanation selector to select, responsive to determining that the network traffic satisfies the multivariate policy, an anomaly explanation.

Abstract: The present application is directed towards systems and methods for adaptive application provisioning for cloud services. An appliance deployed in a network as a gateway may be able to transparently monitor application activity in a cloud computing environment provided by one or more servers, including servers executed by virtual machines, bare-metal or non-virtual servers, or other computing devices. In some embodiments, the appliance may monitor one or more network metrics, including bandwidth usage, latency, congestion, or other issues; and/or may monitor application health or server or virtual machine statistics, including memory and processor usage, bandwidth usage, latency, or other metrics. Responsive to one or more metrics exceeding a threshold, the appliance may automatically provision or start, or deprovision or shut down, one or more virtual or physical machines from a cloud service provider, and may provide configuration information to the provisioned or started machines as needed.

Abstract: The present disclosure is directed towards systems and methods for improving anomaly detection using injected outliers. A normalcy calculator of a device may include a set of outliers into a training dataset of data points. The normalcy calculator, using a K-means clustering algorithm applied on the training dataset, identify at least a first cluster of data points. The normalcy calculator of the device may determine a region with a center and an outer radius that covers at least a spatial extent of the first cluster of data points. The normalcy calculator may determine a first normalcy radius for the first cluster by reducing the region around the center until a point at which all artificial outliers are excluded from a region defined by the first normalcy radius. An outlier detector of the device may use the region defined by the first normalcy radius to determine whether a new data point is normal or abnormal.

Abstract: The present disclosure is directed towards systems and methods for detecting anomalous network traffic. Network traffic corresponding to an application executed by a server can be received. Application characteristics of the application can be identified to select an anomaly detection profile. The anomaly detection profile can be selected based on the identified application characteristics. The anomaly detection profile can include a set of detection features for the anomaly and one or more predetermined threshold values of the detection features. One or more feature values of the set of one or more detection features can be determined. An anomaly in the network traffic can be detected responsive to comparing the feature values and the predetermined threshold values of the detection features.

Abstract: The present disclosure is directed towards systems and methods for characterizing anomalous network traffic. The system includes a device intermediary to clients and servers. The device includes a network traffic engine to receive network traffic including an anomaly. The device includes a univariate policy manager to determine whether the network traffic satisfies at least one of the rules of a univariate policy based on a respective single independent network traffic feature. The device includes a multivariate policy manager to determine, responsive to determining that the network traffic does not satisfy the rules of the univariate policy, that the network satisfies a multivariate policy including a plurality of anomaly explanation tests. The device includes an anomaly explanation selector to select, responsive to determining that the network traffic satisfies the multivariate policy, an anomaly explanation.

Abstract: Systems and methods for protection against session stealing is described. In embodiments of the present solution, a device intermediary to the client and the server may identify first properties of the client and associate the first properties with the session key. When the device receives subsequent request comprising the session key, the device matches the associated first properties with second properties of the second device that is sending the subsequent request. If there is a match, the subsequent request transmitted to the server. Otherwise, the subsequent request is rejected.

Abstract: Utilizing a server-based rules-based action framework, methods and systems gather status and configuration information about each of a plurality of mobile devices, which include devices from different mobile platforms. At the server, software processes monitor status information and respond automatically to changes, causing administrator-selected rules to be evaluated to determine if an action should automatically be initiated.

Abstract: The present application is directed towards systems and methods for adaptive application provisioning for cloud services. An appliance deployed in a network as a gateway may be able to transparently monitor application activity in a cloud computing environment provided by one or more servers, including servers executed by virtual machines, bare-metal or non-virtual servers, or other computing devices. In some embodiments, the appliance may monitor one or more network metrics, including bandwidth usage, latency, congestion, or other issues; and/or may monitor application health or server or virtual machine statistics, including memory and processor usage, bandwidth usage, latency, or other metrics. Responsive to one or more metrics exceeding a threshold, the appliance may automatically provision or start, or deprovision or shut down, one or more virtual or physical machines from a cloud service provider, and may provide configuration information to the provisioned or started machines as needed.

Abstract: Utilizing a server-based rules-based action framework, methods and systems gather status and configuration information about each of a plurality of mobile devices, which include devices from different mobile platforms. At the server, software processes monitor status information and respond automatically to changes, causing administrator-selected rules to be evaluated to determine if an action should automatically be initiated.

Abstract: A streaming rewrite method and system that can execute an efficient multiple pattern search method that parses a response in a data structure of an appliance. The method and system can avoid copying to a buffer by parsing data across a data structure to identify search patterns and phrases that may be identified by one or more actions and/or rules of an appliance or system. A parser can input one or more search patterns, and parse a body of a response or one or more packets for the search patterns. The parser can obtain pattern information about the packets and/or the response, and store this information in a database. The appliance can then perform lookups in the database for pattern information and perform rewrites in accordance with the stored pattern information. The rewritten response and/or packets can then be transmitted to a destination.