Abstract: A method, apparatus and computer program product to protect a deep neural network (DNN) having a plurality of layers including one or more intermediate layers. In this approach, a training data set is received. During training of the DNN using the received training data set, a representation of activations associated with an intermediate layer is recorded. For at least one or more of the representations, a separate classifier (model) is trained. The classifiers, collectively, are used to train an outlier detection model. Following training, the outliner detection model is used to detect an adversarial input on the deep neural network. The outlier detection model generates a prediction, and an indicator whether a given input is the adversarial input. According to a further aspect, an action is taken to protect a deployed system associated with the DNN in response to detection of the adversary input.

Abstract: Malware is detected and mitigated by differentiating HTTP error generation patterns between errors generated by malware, and errors generated by benign users/software. In one embodiment, a malware detector system receives traffic that includes HTTP errors and successful HTTP requests. Error traffic and the successful request traffic are segmented for further analysis. The error traffic is supplied to a clustering component, which groups the errors, e.g., based on their URI pages and parameters. During clustering, various statistical features are extracted (as feature vectors) from one or more perspectives, namely, error provenance, error generation, and error recovery. The feature vectors are supplied to a classifier component, which is trained to distinguish malware-generated errors from benign errors. Once trained, the classifier takes an error cluster and its surrounding successful HTTP requests as inputs, and it produces a verdict on whether a particular cluster is malicious.

Abstract: An intrusion detection system (IDS) for a micro-services environment identifies attacks in substantially real-time and at a container-level. In this approach, behavior models are generated from container images using a binary analysis. A behavior model is a graph data structure having nodes and edges, wherein an edge represents a system call made by at least one process represented as a node in the graph data structure. The model is co-located with a running container, thereby enabling detection of anomalies as the container executes in a container environment on a hardware node. A per-container IDS function is instantiated by checking whether system call telemetry generated by an image's running container satisfies the associated behavior model that has been generated for the container image. If the telemetry indicates activity that deviates from the behavior model, an automated action is then initiated to attempt to address the attack, preferably while it is in progress.

Abstract: A method for improving a detection of beaconing activity includes receiving input data into a computer-implemented processing procedure at least one listing of at least one of time series data and candidate periods of potential beaconing activity. The input data is processed, to detect candidates of potential beaconing activity. By further evaluating the time series data using techniques used for evaluating an analog signal, the performance of detecting of potential beaconing activity is improved to eliminate false positive indications of beaconing activity and/or to provide indication of multiple interleaved periodicities of beaconing.

Abstract: A computer-implemented method, a computer program product, and a computer system. The computer system installs and configures a virtual imitating resource in the computer system, wherein the virtual imitating resource imitates a set of resources in the computer system. Installing and configuring the virtual imitating resource includes modifying respective values of an installed version of the virtual imitating resource for an environment of the computer system, determining whether the virtual imitating resource is a static imitating resource or a dynamic imitating resource, and comparing a call graph of the evasive malware with patterns of dynamic imitating resources on a database. The computer system returns a response from an appropriate element of the virtual imitating resource, in response to a call from the evasive malware to a real computing resource, return, by the computer system.

Abstract: A method, system and apparatus for software intelligence as-a-service, including decomposing software into functional blocks to provide a software genome, building a representation of the software genome in a knowledge graph linking granularities of the functional blocks, and identifying issues with a target software based on the knowledge graph.

Abstract: This disclosure provides for a signal flow analysis-based exploration of security knowledge represented in a graph structure comprising nodes and edges. “Conductance” values are associated to each of a set of edges. Each node has an associated “toxicity” value representing a degree of maliciousness associated with the node. The conductance value associated with an edge is a function of at least the toxicity values of the nodes to which the edge is incident. A signal flow analysis is conducted with respect to an input node representing an observable associated with an offense. The flow analysis seeks to identify a subset of the nodes that, based on their conductance values, are reached by flow of a signal representing a threat, wherein signal flow over a path in the graph continues until a signal threshold is met. Based on the analysis, nodes within the subset are designated as hypothesis nodes for further examination.

Abstract: A cognitive security analytics platform is enhanced by providing a technique for automatically inferring temporal relationship data for cybersecurity events. In operation, a description of a security event is received, typically as unstructured security content or data. Information such as temporal data or cues, are extracted from the description, along with security entity and relationship data. Extracted temporal information is processing according to a set of temporal markers (heuristics) to determine a time value marker (i.e., an established time) of the security event. This processing typically involves retrieval of information from one or more structured data sources. The established time is linked to the security entities and relationships. The resulting security event, as augmented with the identified temporal data, is then subjected to a management operation.

Abstract: A method to detect anomalous behavior in an execution environment. A set of system events captured from a monitored computing system are received. Using the received system events, a model is then trained using machine learning. The model is trained to automatically extract one or more features for the received set of system events, wherein a system event feature is determined by a semantic analysis and represents a semantic relationship between or among a grouping of system events that are observed to co-occur in an observation sample. An observation sample is associated with an operating scenario that has occurred in the execution environment. Once trained, and using the features, the model is used to detect anomalous behavior. As an optimization, prior to training, the set of system events are pre-processed into a reduced set of system events. The modeler may comprise a component of a malware detection system.

Abstract: An automated technique for security monitoring leverages a labeled semi-directed temporal graph derived from system-generated events. The temporal graph is mined to derive process-centric subgraphs, with each subgraph consisting of events related to a process. The subgraphs are then processed to identify atomic operations shared by the processes, wherein an atomic operation comprises a sequence of system-generated events that provide an objective context of interest. The temporal graph is then reconstructed by substituting the identified atomic operations derived from the subgraphs for the edges in the original temporal graph, thereby generating a reconstructed temporal graph. Using graph embedding, the reconstructed graph is converted into a representation suitable for further machine learning, e.g., using a deep neural network. The network is then trained to learn the intention underlying the temporal graph.

Abstract: A computer system trains an Artificial Intelligence (AI) model to generate a key generated as a same key based on multiple different feature vectors, which are based on specified target environment attributes of a target environment domain. The computer system uses the key to encrypt concealed information as an encrypted payload and distributes the encrypted payload and the trained AI model to another computer system. The other computer system extracts environment attributes based on an environment domain accessible by the other computer system and decodes a candidate key by using the trained AI model that uses the extracted environment attributes of the environment domain as input. The trained AI model is trained to generate a key that is generated as a same key from multiple different feature vectors corresponding to specified target environment attributes of a target environment domain. The other computer system determines whether the candidate key is correct.

Abstract: Unknown and reference signatures are accessed. The unknown and reference signatures indicate patterns that correspond to known threats to resources (such as computer systems and/or computer networks) in a computer environment and comprise a multitude of descriptive elements having information describing different aspects of a corresponding signature. A set of similarity measures is created of the unknown and reference signatures from different perspectives, each perspective corresponding to a descriptive element. The set of similarity measures are integrated to generate an overall similarity metric. The overall similarity metric is used to find appropriate categories in the reference signatures into which the unknown signatures should be placed. The unknown signatures are placed into the appropriate categories to create a mapping from the unknown signatures to the reference signatures.

Abstract: Unknown and reference signatures are accessed. The unknown and reference signatures indicate patterns that correspond to known threats to resources (such as computer systems and/or computer networks) in a computer environment and comprise a multitude of descriptive elements having information describing different aspects of a corresponding signature. A set of similarity measures is created of the unknown and reference signatures from different perspectives, each perspective corresponding to a descriptive element. The set of similarity measures are integrated to generate an overall similarity metric. The overall similarity metric is used to find appropriate categories in the reference signatures into which the unknown signatures should be placed. The unknown signatures are placed into the appropriate categories to create a mapping from the unknown signatures to the reference signatures.

Abstract: A cloud based implemented method (and apparatus) includes receiving input data including bipartite graph data in a format of source MAC (Media Access Control) address data versus destination IP (Internet Protocol) data and timestamp information, and providing the input bipartite graph data into a first processing to detect malicious beaconing activities using a lockstep detection module on the input bipartite graph data, as executed in a cloud environment, to detect possible synchronized attacks against a targeted infrastructure.

Abstract: An automated method for processing security events in association with a cybersecurity knowledge graph. The method begins upon receipt of information from a security system representing an offense. An initial offense context graph is built based in part on context data about the offense. The graph also activity nodes connected to a root node; at least one activity node includes an observable. The root node and its one or more activity nodes represent a context for the offense. The knowledge graph, and potentially other data sources, are then explored to further refine the initial graph to generate a refined graph that is then provided to an analyst for further review and analysis. Knowledge graph exploration involves locating the observables and their connections in the knowledge graph, determining that they are associated with known malicious entities, and then building subgraphs that are then merged into the initial graph.

Abstract: A computer-implemented method (and apparatus) includes receiving input data comprising bipartite graph data in a format of source MAC (Machine Access Code) data versus destination IP (Internet Protocol) data and timestamp information. The input bipartite graph data is provided into a first processing to detect malicious beaconing activities using a lockstep detection method on the input bipartite graph data to detect possible synchronized attacks against a targeted infrastructure. The input bipartite graph data is also provided into a second processing, the second processing initially converting the bipartite graph data into a co-occurrence graph format that indicates in a graph format how devices in the targeted infrastructure communicate with different external destination servers over time. The second processing detects malicious beaconing activities by analyzing data exchanges with the external destination servers to detect anomalies.

Abstract: A command endpoint used by Domain Generation Algorithm (DGA) malware is identified using machine learning-based clustering. According to this technique, at least one attribute associated with a candidate resolved DNS name is identified. The candidate resolved DNS name has associated therewith a set of names that are failed DNS lookups but that cluster with the candidate resolved DNS name. A set of additional names that share the at least one attribute with the candidate resolved DNS name are then identified. For the set of additional names, an extent to which the set of additional names also clusters with the set of names that are failed DNS lookups is then determined. The candidate resolved DNS name is characterized as associated with the command endpoint when the set of additional names cluster with the set of names that are failed DNS lookups to a configurable degree.

Abstract: A cognitive security analytics platform is enhanced by providing a technique for automatically inferring temporal relationship data for cybersecurity events. In operation, a description of a security event is received, typically as unstructured security content or data. Information such as temporal data or cues, are extracted from the description, along with security entity and relationship data. Extracted temporal information is processing according to a set of temporal markers (heuristics) to determine a time value marker (i.e., an established time) of the security event. This processing typically involves retrieval of information from one or more structured data sources. The established time is linked to the security entities and relationships. The resulting security event, as augmented with the identified temporal data, is then subjected to a management operation.

Abstract: A cognitive security analytics platform is enhanced by providing a computationally- and storage-efficient data mining technique to improve the confidence and support for one or more hypotheses presented to a security analyst. The approach herein enables the security analyst to more readily validate a hypothesis and thereby corroborate threat assertions to identify the true causes of a security offense or alert. The data mining technique is entirely automated but involves an efficient search strategy that significantly reduces the number of data queries to be made against a data store of historical data. To this end, the algorithm makes use of maliciousness information attached to each hypothesis, and it uses a confidence schema to sequentially test indicators of a given hypothesis to generate a rank-ordered (by confidence) list of hypotheses to be presented for analysis and response by the security analyst.

Abstract: An automated method for processing security event data in association with a cybersecurity knowledge graph having nodes and edges. It begins by receiving from a security system (e.g., a SIEM) information representing an offense. An offense context graph is built. Thereafter, and to enhance the offense context graph, given nodes and edges of the knowledge graph are prioritized for traversal based on an encoding captured from a security analyst workflow. This prioritization is defined in a set of weights associated to the graph nodes and edges, and these weights may be derived using machine learning. The offense context graph is then refined by traversing the nodes and edges of the knowledge graph according to a prioritization tailored at least in part by the encoding. In addition to using security analyst workflow to augment generation of weights, preferably the machine learning system provides recommendations back to the security analysts to thereby influence their workflow.