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: A technique for storage-efficient cyber incident reasoning by graph matching. The method begins with a graph pattern that comprises a set of elements with constraints and connections among them. A graph of constraint relations (GoC) in the graph pattern is derived. An activity graph representing activity data captured in association with a host machine is then obtained. In response to a query, one or more subgraphs of the activity graph that satisfy the graph pattern are then located and, in particular, by iteratively solving constraints in the graph pattern. In particular, a single element constraint is solved to generate a result, and that result is propagated to connected constraints in the graph of constraint relations. This process continues until all single element constraints have been evaluated, and all propagations have been performed. The subgraphs of the activity graph that result are then returned in response to a database query.

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: Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.

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: An automated method for processing security events. It begins by building an initial version of a knowledge graph based on security information received from structured data sources. Using entities identified in the initial version, additional security information is then received. The additional information is extracted from one or more unstructured data sources. The additional information includes text in which the entities (from the structured data sources) appear. The text is processed to extract relationships involving the entities (from the structured data sources) to generate entities and relationships extracted from the unstructured data sources. The initial version of the knowledge graph is then augmented with the entities and relationships extracted from the unstructured data sources to build a new version of the knowledge graph that consolidates the intelligence received from the structured data sources and the unstructured data sources. The new version is then used to process security event data.

Abstract: A stackable filesystem that transparently tracks process file writes for forensic analysis. The filesystem comprises a base filesystem, and an overlay filesystem. Processes see the union of the upper and lower filesystems, but process writes are only reflected in the overlay. By providing per-process views of the filesystem using this stackable approach, a forensic analyzer can record a process's file-based activity—i.e., file creation, deletion, modification. These activities are then analyzed to identify indicators of compromise (IoCs). These indicators are then fed into a forensics analysis engine, which then quickly decides whether a subject (e.g., process, user) is malicious. If so, the system takes some proactive action to alert a proper authority, to quarantine the potential attack, or to provide other remediation. The approach enables forensic analysis without requiring file access mediation, or conducting system event-level collection and analysis, making it a lightweight, and non-intrusive solution.

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: Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.

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: USB traffic is intercepted between a USB device and a computer system. It is determined whether the USB device has previously had a policy associated with it as to whether USB traffic from the device should be blocked, allowed, or sanitized. In response to not having a previous policy for the USB device, a request is made for a user to be prompted to provide a policy of one of block, allow, or sanitize for the USB device. In response to a user-provided-policy, one of the following are performed: blocking the traffic, allowing the traffic, or sanitizing the traffic between the USB device and the computer system. Apparatus, methods, and computer program products are disclosed.

Abstract: Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.

Abstract: Advanced Persistent Threat (APT) defense leverages priority-based tracking around alerts, together with priority-based alert reasoning task scheduling. In one embodiment, individual alert reasoning tasks are managed by an alert scheduler, which effectively allocates available computation resources to prioritize the alert reasoning tasks, which each execute within processing workers that are controlled by the alert scheduler. An alert reasoning task typically is prioritized (relative to other such tasks) according to one or more factors, such as severity levels, elapsed time, and other tracking results. By implementing priority-based task scheduling, the task scheduler provides for alert reasoning tasks that are interruptible. In this approach, and once an alert is assigned to a task and the task assigned a worker, priority-based connectivity tracker around each alert is carried out to provide further computational efficiency.

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: An interactive display system enables a user to compose a graph pattern for a temporal graph on a display screen. The system comprises a canvas that provides an interactive editing surface. The editor receives an input a set of user interactions, such as the drawing of lines and boxes, the specifying of attributes, and the like, that together compose a graph pattern. During the graph pattern composition, the user may retrieve other graph patterns (e.g., from a data store) and integrate them into the pattern being composed. Once the graph pattern is composed (or as it is being composed), the system converts the graphical pattern into a text-based representation, such as a computer program in a particular graph programming language, which is then used for subsequent processing and matching in a cybersecurity threat discovery workflow. The pattern (program code) also is stored to disk, from which it may be retrieved and converted back into its graphical view on the screen, e.g., for further editing and revision.

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 automated method for cyberattack detection and prevention in an endpoint. The technique monitors and protects the endpoint by recording inter-process events, creating an inter-process activity graph based on the recorded inter-process events, matching the inter-process activity (as represented in the activity graph) against known malicious or suspicious behavior (as embodied in a set of one or more pattern graphs), and performing a post-detection operation in response to a match between an inter-process activity and a known malicious or suspicious behavior pattern. Preferably, matching involves matching a subgraph in the activity graph with a known malicious or suspicious behavior pattern as represented in the pattern graph. During this processing, preferably both direct and indirect inter-process activities at the endpoint (or across a set of endpoints) are compared to the known behavior patterns.

Abstract: A decoy filesystem that curtails data theft and ensures file integrity protection through deception is described. To protect a base filesystem, the approach herein involves transparently creating multiple levels of stacking to enable various protection features, namely, monitoring file accesses, hiding and redacting sensitive files with baits, and injecting decoys onto fake system views that are purveyed to untrusted subjects, all while maintaining a pristine state to legitimate processes. In one implementation, a kernel hot-patch is used to seamlessly integrate the new filesystem module into live and existing environments.

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.