Abstract: In one aspect, a method includes receiving a packet at a first node from a second node, wherein the first node and the second node are part of a network; determining if congestion exists in a primary route used by the packet; processing a packet drop event to establish a secondary route for the packet in response to determining that the congestion exists in the primary route; and restoring use of the primary route if an expiration time has expired. The expiration time is adjusted by an elapsed period and a congestion condition within the network.

Abstract: Techniques for multi-domain systems integration and evaluation are disclosed, including: obtaining criteria associated with a strategic objective; determining that a first system, operating in a first operating domain, is only partially capable of satisfying a first criterion in the criteria; determining that a second system, operating in a second operating domain that is different from the first operating domain, is capable of augmenting the first system with respect to satisfying the first criterion; responsive to determining that the second system is capable of augmenting the first system with respect to satisfying the first criterion, modeling a multi-domain system including at least a first component from the first system and at least a second component from the second system; and generating a performance metric that objectively evaluates capabilities of the multi-domain system against the criteria associated with the strategic objective.

Abstract: Systems, devices, methods, and computer-readable media for normalized (threat, effect) pair algorithm generation. A method can include, for a defined scenario, identifying (threat, effect) pairs and for each (threat, effect) pair of the identified (threat, effect) pairs categorizing metrics of an algorithm, the algorithm indicating a probability of mitigating damage, by the effect, caused by the threat and generating a normalized algorithm for the identified (threat, effect) pair based on the metrics, the normalized algorithm operating based on input parameters of same units as other normalized algorithms.

Abstract: Discussed generally are techniques for managing operation of programs in a sequential order. A method can include receiving a query for an image, the query indicating characteristics of the image, selecting a chain of algorithms configured to identify the image based on the characteristics, operating an algorithm of the selected chain of algorithms that operate in increased fidelity order on an input to produce a first result, operating a ground truth algorithm on the input to generate a second result, comparing the first and second results to determine a probability of correctness (Pc) and confidence interval (CI) for the algorithm, and altering the chain of algorithms based on the determined Pc and CI.

Abstract: Systems, devices, methods, and computer-readable media for concurrent visualization of sensor and communications operations. A method can include receiving mission data indicating a target, a sensor, a communications system, and an operation to be performed regarding the target, identifying one or more operational layer, functional layer, and physical layer models for the sensor and communications system, and a physical layer model for weather, identifying, based on a comparison of the physical models of the sensor and communications system to a propagation equation, any gaps or inconsistencies between the physical models of the sensor and communications system and the propagation equation, and executing a simulation model resulting in a visual display of execution of the mission using the sensor and the communications system, the simulation model generated based on a filler model that fills any identified gaps or fixes any identified inconsistencies.

Abstract: Techniques for machine learning-assisted multi-domain planning are disclosed, including: receiving first situational data from a first domain and second situational data from a second domain; receiving first user input indicating an objective; applying at least the first situational data, the second situational data, and the objective to a machine learning model, to obtain one or more suggested courses of action for satisfying the objective using assets selected from a plurality of assets available in the first domain and the second domain; and presenting the one or more suggested courses of action in a graphical user interface.

Abstract: Techniques for multi-domain systems integration and evaluation are disclosed, including: obtaining criteria associated with a strategic objective; determining that a first system, operating in a first operating domain, is only partially capable of satisfying a first criterion in the criteria; determining that a second system, operating in a second operating domain that is different from the first operating domain, is capable of augmenting the first system with respect to satisfying the first criterion; responsive to determining that the second system is capable of augmenting the first system with respect to satisfying the first criterion, modeling a multi-domain system including at least a first component from the first system and at least a second component from the second system; and generating a performance metric that objectively evaluates capabilities of the multi-domain system against the criteria associated with the strategic objective.

Abstract: Discussed herein are devices, systems, and methods for autonomous, dynamic course of action (COA) generation and management. A method can include issuing a communication to one or more assets indicating operations of a first COA to be performed, receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred, in response to the data indicating the unexpected event, identifying a second COA or a portion of a second COA that satisfies a mission of the first COA and accounts for the unexpected event, and issuing a second communication to the one or more assets indicating one or more operations of the second COA to be performed.

Abstract: Evidence decay in PGMs is achieved using virtual evidence nodes that create and send lambda messages that when combined with the other evidence force specified beliefs onto the decaying evidence nodes. The virtual evidence nodes compute a step along a path from the decaying node's current belief to a target belief to determine the specified belief. Belief propagation is executed to process the pi and lambda messages to update the current beliefs for all nodes. Observation evidence is removed from the model. For each decaying node, belief propagation is executed absent the evidence of that node to generate an updated target belief. Following an observation, the node's belief will decay in a smooth, continuous manner.

Abstract: Discussed herein are devices, systems, and methods for autonomous, dynamic course of action (COA) generation and management. A method can include issuing a communication to one or more assets indicating operations of a first COA to be performed, receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred, in response to the data indicating the unexpected event, identifying a second COA or a portion of a second COA that satisfies a mission of the first COA and accounts for the unexpected event, and issuing a second communication to the one or more assets indicating one or more operations of the second COA to be performed.

Abstract: Discussed generally are techniques for managing operation of programs in a sequential order. A method can include receiving a query for an image, the query indicating characteristics of the image, selecting a chain of algorithms configured to identify the image based on the characteristics, operating an algorithm of the selected chain of algorithms that operate in increased fidelity order on an input to produce a first result, operating a ground truth algorithm on the input to generate a second result, comparing the first and second results to determine a probability of correctness (Pc) and confidence interval (CI) for the algorithm, and altering the chain of algorithms based on the determined Pc and CI.

Abstract: A computing machine stores representations of a plurality of assets. The computing machine receives a representation of a course of action (COA), the COA making use of all or a subset of the plurality of assets, a representation of movement of the all or the subset of the plurality of assets across time, and a goal. The computing machine identifies one or more mission phases and/or activities in the COA and one or more assets or asset pairings for use in each mission phase and/or activity. The computing machine computes a set of values for a given mission phase and/or activity. The computing machine logs the computed set of values. The computing machine stores metrics representing the computed set of values and the one or more mission phases and/or activities in the COA. The metrics are used to verify the results of the computations.

Abstract: A system and method improves the probability of correctly detecting an object from a collection of source data and reduces the processing load. A plurality of algorithms for a given data type are selected and ordered based on a cumulative trained probability of correctness (Pc) that each of the algorithms, which are processed in a chain and conditioned upon the result of the preceding algorithms, produce a correct result and a processing. The algorithms cull the source data to pass forward a reduced subset of source data in which the conditional probability of detecting the object is higher than the a priori probability of the algorithm detecting that same object. The Pc and its confidence interval is suitably computed and displayed for each algorithm and the chain and the final object detection.

Abstract: Generally discussed herein are systems, devices, and methods for mitigating damage caused by a hazard. A method can include identifying at least two effects that, with some probability, at least partially mitigate the hazard, identifying one or more vulnerabilities of the hazard that are the target for an effect of the identified effects, for each hazard, vulnerability pair, identifying a respective hazard model that simulates a state of the hazard in response to the effect, identifying effect models that simulate the respective effects, normalizing each of the identified effect models to a common model and determining a confidence level for each parameter of each normalized model, and simulating combinations of effects by combining normalized models and recording their combined effect on the hazard and a corresponding combined confidence level for the normalized models.

Abstract: Embodiments of a method and apparatus for eliminating a missile threat are generally described herein. In some embodiments, the method includes identifying a vulnerability associated with the missile threat. The method can further include identifying a technique for exploiting the vulnerability to generate a vulnerability-technique (VT) pair. The method can further include applying a stochastic mathematical model (SMM) to generate a negation value, the negation value being representative of a probability that the technique of the respective VT pair will eliminate the threat by exploiting the vulnerability. The method can further include providing a recommendation for implementation the technique to eliminate the missile threat responsive to receiving a user selection of the technique, the user selection being selected based on the generated negation value. Other example methods, systems, and apparatuses are described.

Abstract: A method of fusing sensor detection probabilities. The fusing of detection probabilities may allow a first force to detect an imminent threat from a second force, with enough time to counter the threat. The detection probabilities may include accuracy probability of one or more sensors and an available time probability of the one or more sensors. The detection probabilities allow a determination of accuracy of intelligence gathered by each of the sensors. Also, the detection probabilities allow a determination of a probable benefit of an additional platform, sensor, or processing method. The detection probabilities allow a system or mission analyst to quickly decompose a problem space and build a detailed analysis of a scenario under different conditions including technology and environmental factors.

Abstract: Embodiments of an apparatus and method for assessing non-kinetic weapon performance for negating missile threats are generally described herein. In some embodiments, vulnerabilities of missile threats and techniques for negating the threats are identified. A probability of negation associated with an effectiveness of each of the techniques against the vulnerabilities is calculated. The calculated probability of negation of each technique against each vulnerability are conditioned at a plurality of times associated with a plurality of asymmetric missile defense (AMD) layer elements to produce temporal level probabilities of negation. Each temporal level probabilities of negation are conditioned based on a probability of validation of deployment and a probability of verification of mitigation to produce a battle damage assessment probability of negation.

Abstract: A method for accurately determining whether a response tool will be effective for responding to a given enemy threat object. Embodiments described herein provide a method and system for responding to a threat object, for example, negating missile threats. Embodiments may include validating effectiveness of a response to the threat object. Other embodiments may include verifying the continued effectiveness of a response to the threat object. Further embodiments may include providing feedback to re-perform the method for responding to the threat object. The system may include a mathematical method, and associated algorithms, to assess, in an automated fashion, the performance of non-kinetic techniques with respect to negating the threat object.

Abstract: A system and method improves the probability of correctly detecting an object from a collection of source data and reduces the processing load. A plurality of algorithms for a given data type are selected and ordered based on a cumulative trained probability of correctness (Pc) that each of the algorithms, which are processed in a chain and conditioned upon the result of the preceding algorithms, produce a correct result and a processing. The algorithms cull the source data to pass forward a reduced subset of source data in which the conditional probability of detecting the object is higher than the a priori probability of the algorithm detecting that same object. The Pc and its confidence interval is suitably computed and displayed for each algorithm and the chain and the final object detection.

Abstract: A method of rapidly producing a new cyber response tool (e.g., in near-real-time) by matching vulnerabilities of enemy threats (e.g., a missile and/or a tank) to corresponding portions of other response tools that effectively exploit the matched vulnerability. An iterative framework may be utilized to repeatedly prioritize a set of cyber response tools based on a corresponding probability of success. For example, a computer or computer network may implement the iterative framework to carry out the probability computation and corresponding cyber response tool prioritization. If a total probability of success is below a given threshold (e.g., 95%), then creation of one or more new cyber response tools may be initiated. The probability of success may be a function of time (e.g., ten minutes before an expected launch) and/or a function of a phase of a lifecycle of the enemy threat (e.g., a launch phase).