Abstract: A method includes collecting system calls and call parameters invoked by monitored applications for target computer systems. The system calls and call parameters are received from operating system kernels on the plurality of target computer systems. Sequences of systems calls and call parameters of the monitored applications are correlated among different target computer systems to deduce malicious activities. Remedial action(s) are performed in response to malicious activities being deduced as being malicious by the correlating. Another method includes determining that network activity at a specific time is deemed to be suspicious. Using IP addresses involved in the suspicious network activity, computer system(s) are determined that are sources of the suspicious network activity. Based on the specific time and the determined computer system(s), application(s) are determined that are executing on the determined computer system(s) that are causing the suspicious network activity.

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: Decoy network ports and services are projected onto existing production workloads to facilitate cyber deception, without the need to modify production machines. The approach may be implemented in a production network that includes two segments. A production machine is reachable via the first segment, while a decoy machine that offers the network service expected from the production machine is reachable via the second segment. A deception router is configured in front of the two segments, and it is not visible on the link and network layers. The router inspects network traffic destined for the production machine. Based on a set of one or more conditions being met, the router determines whether to relay network packets to the production machine, or to redirect the packet to the decoy machine.

Abstract: This disclosure provides for rapid deployments of application-level deceptions (i.e., booby traps) to implant cyber deceptions into running legacy applications both on production and decoy systems, with no downtime and minimal performance overhead compared with the original application. An application-level booby trap is a piece of code injected into an application, and which provides an active defense or deception in response to an attack. A booby trap does not influence program execution under normal operation, and preferably elicits a response that can be defined by a security analyst. In operation, a booby trap is compiled into a bitcode using a patch synthesis process, and it is then injected into a running application, where it is compiled further into machine code, and linked directly with the existing application constructs. The original function also is modified with a function trampoline, and subsequent calls to the original function are then directed to the new function.

Abstract: Rapid deployments of application-level deceptions (i.e., booby traps) implant cyber deceptions into running legacy applications both on production and decoy systems. Once a booby trap is tripped, the affected code is moved into a decoy sandbox for further monitoring and forensics. To this end, this disclosure provides for unprivileged, lightweight application sandboxing to facilitate monitoring and analysis of attacks as they occur, all without the overhead of current state-of-the-art approaches. Preferably, the approach transparently moves the suspicious process to an embedded decoy sandbox, with no disruption of the application workflow (i.e., no process restart or reload). Further, the action of switching execution from the original operating environment to the sandbox preferably is triggered from within the running process.

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 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 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 method (and system) of scoring asset risk including modeling an interdependence of risks of a plurality of entities within a network by modeling the network as a graph connecting different entities, the different entities are selected from a group of a user, a device, a credential, a high-value asset, and an external server, the graph being defined as a set of vertices comprising the user, the device, the credential, the high-value asset, and the external server and a set of edges represented by an N-by-N adjacency matrix with each pair of the entities sharing a relationship and applying a Belief Propagation (BP) algorithm for solving the inference problem over the graph by inferring the risk from the entities own properties and surrounding entities with the shared relationship in the adjacency matrix, the Belief Propagation algorithm obtains risk information related to each entity of the plurality of entities.

Abstract: A method includes collecting system calls and call parameters invoked by monitored applications for target computer systems. The system calls and call parameters are received from operating system kernels on the plurality of target computer systems. Sequences of systems calls and call parameters of the monitored applications are correlated among different target computer systems to deduce malicious activities. Remedial action(s) are performed in response to malicious activities being deduced as being malicious by the correlating. Another method includes determining that network activity at a specific time is deemed to be suspicious. Using IP addresses involved in the suspicious network activity, computer system(s) are determined that are sources of the suspicious network activity. Based on the specific time and the determined computer system(s), application(s) are determined that are executing on the determined computer system(s) that are causing the suspicious network activity.

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 distributed feature collection and correlation engine is provided, Feature extraction comprises obtaining one or more data records; extracting information from the one or more data records based on domain knowledge; transforming the extracted information into a key/value pair comprised of a key K and a value V, wherein the key comprises a feature identifier; and storing the key/value pair in a feature store database if the key/value pair does not already exist in the feature store database using a de-duplication mechanism. Features extracted from data records can be queried by obtaining a feature store database comprised of the extracted features stored as a key/value pair comprised of a key K and a value V, wherein the key comprises a feature identifier; receiving a query comprised of at least one query key; retrieving values from the feature store database that match the query key; and returning one or more retrieved key/value pairs.

Abstract: A distributed feature collection and correlation engine is provided, Feature extraction comprises obtaining one or more data records; extracting information from the one or more data records based on domain knowledge; transforming the extracted information into a key/value pair comprised of a key K and a value V, wherein the key comprises a feature identifier; and storing the key/value pair in a feature store database if the key/value pair does not already exist in the feature store database using a de-duplication mechanism. Features extracted from data records can be queried by obtaining a feature store database comprised of the extracted features stored as a key/value pair comprised of a key K and a value V, wherein the key comprises a feature identifier; receiving a query comprised of at least one query key; retrieving values from the feature store database that match the query key; and returning one or more retrieved key/value pairs.

Abstract: A method includes collecting system calls and call parameters invoked by monitored applications for target computer systems. The system calls and call parameters are received from operating system kernels on the plurality of target computer systems. Sequences of systems calls and call parameters of the monitored applications are correlated among different target computer systems to deduce malicious activities. Remedial action(s) are performed in response to malicious activities being deduced as being malicious by the correlating. Another method includes determining that network activity at a specific time is deemed to be suspicious. Using IP addresses involved in the suspicious network activity, computer system(s) are determined that are sources of the suspicious network activity. Based on the specific time and the determined computer system(s), application(s) are determined that are executing on the determined computer system(s) that are causing the suspicious network activity.

Abstract: A method for identifying an unknown user according to a plurality of facets of user activity in a plurality of contexts includes receiving a plurality of priors for the facets with respect to the contexts, receiving a plurality of footprints of known users, aggregating the footprints of the users to determine an ensemble prior, receiving a plurality of network traces relevant to an unknown user in a computer environment, matching the network traces against each of the footprints to determine a plurality of matches, aggregating the matches using the ensemble prior according to the facets and the contexts, and outputting a probable user identity for the unknown user.

Abstract: A method (and system) of scoring asset risk includes determining, using a processor, a risk value for each entity of a plurality of entities within a network and ranking each risk value.

Abstract: A method includes collecting system calls and call parameters invoked by monitored applications for target computer systems. The system calls and call parameters are received from operating system kernels on the plurality of target computer systems. Sequences of systems calls and call parameters of the monitored applications are correlated among different target computer systems to deduce malicious activities. Remedial action(s) are performed in response to malicious activities being deduced as being malicious by the correlating. Another method includes determining that network activity at a specific time is deemed to be suspicious. Using IP addresses involved in the suspicious network activity, computer system(s) are determined that are sources of the suspicious network activity. Based on the specific time and the determined computer system(s), application(s) are determined that are executing on the determined computer system(s) that are causing the suspicious network activity.

Abstract: A method for identifying an unknown user according to a plurality of facets of user activity in a plurality of contexts includes receiving a plurality of priors for the facets with respect to the contexts, receiving a plurality of footprints of known users, aggregating the footprints of the users to determine an ensemble prior, receiving a plurality of network traces relevant to an unknown user in a computer environment, matching the network traces against each of the footprints to determine a plurality of matches, aggregating the matches using the ensemble prior according to the facets and the contexts, and outputting a probable user identity for the unknown user.

Abstract: Methods and apparatus are provided for detecting unauthorized bulk forwarding of sensitive data over a network. A bulk forwarding of email from a first network environment is automatically detected by determining an arrival rate for internal emails received from within the first network environment into one or more user accounts; determining a sending rate for external emails sent from the one or more user accounts to a second network environment; and detecting the bulk forwarding of email from a given user account by comparing the arrival rate for internal emails and the sending rate for external emails. The bulk forwarding of email from a given user account can be detected by determining whether statistical models of the arrival rate for internal emails and of the sending rate for external emails are correlated in time.

Abstract: Methods and apparatus are provided for detecting unauthorized bulk forwarding of sensitive data over a network. A bulk forwarding of email from a first network environment is automatically detected by determining an arrival rate for internal emails received from within the first network environment into one or more user accounts; determining a sending rate for external emails sent from the one or more user accounts to a second network environment; and detecting the bulk forwarding of email from a given user account by comparing the arrival rate for internal emails and the sending rate for external emails. The bulk forwarding of email from a given user account can be detected by determining whether statistical models of the arrival rate for internal emails and of the sending rate for external emails are correlated in time.