Abstract: A method includes training a first machine learning model with a first dataset, to produce a first trained machine learning model to infer cybersecurity-oriented file properties and/or detect cybersecurity threats within a first domain. The first dataset includes labeled files associated with the first domain. The first trained machine learning model includes multiple layers, some of which are trainable. A second trained machine learning model is generated, via a transfer learning process, using (1) at least one trainable layer from the multiple trainable layers of the first trained machine learning model, and (2) a second dataset different from the first dataset. The second dataset includes labeled files associated with a second domain. The first domain has a different syntax, different semantics, and/or a different structure than that of the second domain. The second trained machine learning model (e.g.

Abstract: Techniques for performing cyber-security alert analysis and prioritization according to machine learning employing a predictive model to implement a self-learning feedback loop. The system implements a method generating the predictive model associated with alert classifications and/or actions which automatically generated, or manually selected by cyber-security analysts. The predictive model is used to determine a priority for display to the cyber-security analyst and to obtain the input of the cyber-security analyst to improve the predictive model. Thereby the method implements a self-learning feedback loop to receive cyber-security alerts and mitigate the cyberthreats represented in the cybersecurity alerts.

Abstract: A system for detecting whether a file including content is associated with a cyber-attack is described. The content may include an executable file for example. The system includes an intelligence-driven analysis subsystem and a computation analysis subsystem. The intelligence-driven analysis subsystem is configured to (i) receive the file, (ii) inspect and compute features of the file for indicators associated with a cyber-attack, and (iii) produce a first output representing the detected indicators. The computational analysis subsystem includes an artificial neural network to (i) receive a network input being a first representation of at least one section of binary code from the file as input, and (ii) process the first representation of the section to produce a second output. The first output and the second output are used in determination a classification assigned to the file.

Abstract: The presently disclosed subject matter includes a system for monitoring a set of command lines or calls to executable scripts configured to be executed by an operating system. Each command line from the set of command lines is associated with an executable script configured to be executed by an operating system. The apparatus classifies, via a machine learning model, a command line from the set of command lines into an obfuscation category and prevents the operating system from executing the command line and generates a notification signal when the obfuscation category indicates that the command line is part of a cybersecurity attack. The apparatus allows the operating system to execute the command line or call to the executable script when the obfuscation category indicates that the command line is not part of a cybersecurity attack.

Abstract: Churn-aware training of a classifier which reduces the difference between predictions of two different models, such as a prior generation of a classification model and a subsequent generation. A second dataset of labelled data is scored on a prior generation of a classification model, wherein the prior generation was trained on a first dataset of labelled data. A subsequent generation of a classification model is trained with the second dataset of labelled data, wherein in training of the subsequent generation, weighting of at least some of the labelled data in the second dataset, such as labelled data threat yielded an incorrect classification, is adjusted based on the score of such labelled data in the prior generation.

Abstract: An automated system and method for analyzing a set of extracted strings from a binary is disclosed including processing the binary with a string-extraction logic that can locate strings within the binary and output an extracted string set for use in cybersecurity analysis. The logic retrieves a set of training data comprising a plurality of previously analyzed extracted string sets where each element of the previously analyzed extracted string set comprises at least one extracted string and a corresponding previously determined threat prediction score. A prediction model based upon the training data is generated and the extracted string set is processed by the prediction model to determine a threat prediction score for each string. Ranking of the located strings is based upon the determined threat prediction score, and an output of a ranked string list is generated.

Abstract: A method includes training a first machine learning model with a first dataset, to produce a first trained machine learning model to infer cybersecurity-oriented file properties and/or detect cybersecurity threats within a first domain. The first dataset includes labeled files associated with the first domain. The first trained machine learning model includes multiple layers, some of which are trainable. A second trained machine learning model is generated, via a transfer learning process, using (1) at least one trainable layer from the multiple trainable layers of the first trained machine learning model, and (2) a second dataset different from the first dataset. The second dataset includes labeled files associated with a second domain. The first domain has a different syntax, different semantics, and/or a different structure than that of the second domain. The second trained machine learning model (e.g.

Abstract: The disclosure is directed to a system for testing known bad destinations while in a production network. The system can include a source controller and a destination controller in a production network. The source controller and the destination controller can have a configuration of a predetermined set of one or more known bad external destinations to test a security control device of the production network intermediary to the source controller and the destination controller. The source controller can be configured to communicate test traffic generated to a known bad external destination. The test traffic can pass through the security control device with a network identifier of the known bad external destination. The destination controller can be configured to receive the test traffic forwarded by a network device of the production network.

Abstract: A computerized method for associating cyberthreat actor groups responsible for different cyberthreats is described. The method involves generating a similarity matrix based on content from received clusters of cybersecurity information. Each received cluster of cybersecurity information is assumed to be associated with a cyberthreat. The similarity matrix is composed via an optimized equation combining separate similarity metrics, where each similarity metric of the plurality of similarity metrics represents a level of correlation between at least two clusters of cybersecurity information, with respect to a particular aspect of operations described in the clusters. The method further involves that, in response to queries directed to the similarity matrix, generating a listing of a subset of the clusters of cybersecurity information having a greater likelihood of being associated with cyberthreats caused by the same cyberthreat actor group.

Abstract: A method for performing cyber-security analysis includes generating a semantic graph in which each object is represented as a node, and each event associated with an object is represented as an edge. A cyber-threat related alert, with an associated alert type, is received from a source. A first object from the plurality of objects is modified based on the alert. A plurality of threat scores, each associated with an object, are calculated, substantially concurrently, based on the alert type. Subsequently, a plurality of modified threat scores are determined for each object, based on: (1) the threat score for that object, (2) a connectivity of that object to each of the remaining objects within the semantic graph; and (3) the threat score for each remaining object from the plurality of objects. A subgraph of the semantic graph is identified based on normalized versions of the modified threat scores.

Abstract: A system and method for employing memory forensic techniques to determine operating system type, memory management configuration, and virtual machine status on a running computer system. The techniques apply advanced techniques in a fashion to make them usable and accessible by Information Technology professionals that may not necessarily be versed in the specifics of memory forensic methodologies and theory.