Abstract: Under one aspect, a computer-implemented method includes receiving a query at a query interface about whether a computer file comprises malicious code. It is determined, using at least one machine learning sub model corresponding to a type of the computer file, whether the computer file comprises malicious code. Data characterizing the determination are provided to the query interface. Generating the sub model includes receiving computer files at a collection interface. Multiple sub populations of the computer files are generated based on respective types of the computer files, and random training and testing sets are generated from each of the sub populations. At least one sub model for each random training set is generated.

Abstract: An automated framework provides security monitoring and analysis in a network by autonomously detecting actual and potential threats to the network. In response to detection of a threat, the framework instantiates a Situation to provide directed monitoring of the threat. The Situation invokes specific skills based on the state of the Situation to monitor network traffic for activity specific to the threat that instantiated the Situation. As data is collected, additional skills may be invoked based on the additional data to collect new data, and previously invoked skills may be terminated depending on the additional data to avoid collecting information that is no-longer relevant.

Abstract: System and method to identify a security entity in a computing environment is disclosed. Communication between a user computer and at least one destination computer by a security appliance is monitored by a security appliance. A virtual identifier is assigned to a subset of the communication within a defined time period. At least one security entity is identified based on a subset of the selective information. The assigned virtual identifier associated with at least one security entity.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.

Abstract: Described are techniques to enable computers to efficiently determine if they should run a program based on an immediate (i.e., real-time, etc.) analysis of the program. Such an approach leverages highly trained ensemble machine learning algorithms to create a real-time discernment on a combination of static and dynamic features collected from the program, the computer's current environment, and external factors. Related apparatus, systems, techniques and articles are also described.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.

Abstract: System and method to evaluate a plurality of security entities in a network environment is disclosed. Communication between a user computer and a destination computer is monitored by a security appliance. Selective information from the communication is extracted by the security appliance. The selective information is indicative of a value for one or more attributes of the plurality of security entities. A first value indicative of occurrence of each of the values for each of the attributes is generated. A second value indicative of occurrence of each of the values for each of the attributes for each of the security entity is generated. A third value is calculated based on the first value and the second value for each of the attribute value for each of the security entity, wherein the third value is indicative of significance of the value of the attribute for the security entity.

Abstract: Described are techniques to enable computers to efficiently determine if they should run a program based on an immediate (i.e., real-time, etc.) analysis of the program. Such an approach leverages highly trained ensemble machine learning algorithms to create a real-time discernment on a combination of static and dynamic features collected from the program, the computer's current environment, and external factors. Related apparatus, systems, techniques and articles are also described.

Abstract: Described are techniques to enable computers to efficiently determine if they should run a program based on an immediate (i.e., real-time, etc.) analysis of the program. Such an approach leverages highly trained ensemble machine learning algorithms to create a real-time discernment on a combination of static and dynamic features collected from the program, the computer's current environment, and external factors. Related apparatus, systems, techniques and articles are also described.

Abstract: System and method for detecting a likely threat from a malicious attack is disclosed. Communication between a user computer and a destination computer is monitored by a security appliance. Selective information from the communication is extracted. One or more weak signals of a threat is detected based on the selective information. One or more weak signals are evaluated for a likely threat based on a threshold value. A corrective action is initiated for the likely threat, based on the evaluation.

Abstract: System and method for detecting a likely threat from a malicious attack is disclosed. Communication between a user computer and a destination computer is monitored by a security appliance. Selective information from the communication is extracted. Selective information is associated to one or more attributes of a security entity. A knowledge graph is generated for a plurality of security entities based on the associated selective information.

Abstract: System and method for evaluating communication between a plurality of computing devices is disclosed. A plurality of communication between a user computer and at least one a destination computer is monitored by a security appliance. Selective information from the plurality of communication is extracted by the security appliance. Extracted selective information between a pair of communication is compared for a match. An activity record is generated for the user computer and at least one destination computer, based on the match.

Abstract: System and method to identify a security entity in a computing environment is disclosed. Communication between a user computer and at least one destination computer by a security appliance is monitored by a security appliance. Selective information from the communication is extracted by the security appliance. At least one security entity is identified based on a subset of the selective information. One or more selective information is associated to at least one security entity. A knowledge graph is generated based on the associated selective information.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.

Abstract: System and method to characterize a security entity in a computing environment is disclosed. Communication between a user computer and at least one destination computer by a security appliance is monitored by a security appliance. Selective information from the communication is extracted by the security appliance, selective information indicative of the security entity. A plurality of words from the communication between the identified security entity and at least one destination computer are selectively extracted. A word cloud is generated based on the selectively extracted plurality of words. The word cloud is evaluated to characterize the identified security entity.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.

Abstract: Under one aspect, a computer-implemented method includes receiving a query at a query interface about whether a computer file comprises malicious code. It is determined, using at least one machine learning sub model corresponding to a type of the computer file, whether the computer file comprises malicious code. Data characterizing the determination are provided to the query interface. Generating the sub model includes receiving computer files at a collection interface. Multiple sub populations of the computer files are generated based on respective types of the computer files, and random training and testing sets are generated from each of the sub populations. At least one sub model for each random training set is generated.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.

Abstract: Data is received or accessed that includes a structured file encapsulating data required by an execution environment to manage executable code wrapped within the structured file. Thereafter, code and data regions are iteratively identified in the structured file. Such identification is analyzed so that at least one feature can be extracted from the structured file. Related apparatus, systems, techniques and articles are also described.