Martin Kruger

Game Theoretic Approach to Threat Prediction and Situation Awareness

The strategy of data fusion has been applied in threat prediction and situation awareness and the terminology has been standardized by the Joint Directors of Laboratories (JDL) in the form of a so-called JDL data fusion model, which currently called DFIG model. Higher levels of the DFIG model call for prediction of future development and awareness of the development of a situation. It is known that Bayesian network is an insightful approach to determine optimal strategies against asymmetric adversarial opponent. However, it lacks the essential adversarial decision processes perspective. In this paper, a highly innovative data-fusion framework for asymmetric-threat detection and prediction based on advanced knowledge infrastructure and stochastic (Markov) game theory is proposed. In particular, asymmetric and adaptive threats are detected and grouped by intelligent agent and hierarchical entity aggregation in level 2 and their intents are predicted by a decentralized Markov (stochastic) game model with deception in level 3. We have verified that our proposed algorithms are scalable, stable, and perform satisfactorily according to the situation awareness performance metric

Game-theoretic modeling and control of military operations with partially emotional civilian players

Civilians are not just passively static but might purposefully take actions to help one side in a battle. Sometimes civilians might directly join one side if they are excessively agitated by the other side. In this paper, a three-player attrition-type discrete time dynamic game model is formulated, in which there are two opposing forces and one civilian player that might be neutral, biased, or even joining one side publicly. Emotions of civilians are dynamically updated via anger mechanism. An example scenario and extensive simulations illustrate possible applications of this model, and comparative discussions further clarify the benefits.

A Markov game theoretic data fusion approach for cyber situational awareness

This paper proposes an innovative data-fusion/ data-mining game theoretic situation awareness and impact assessment approach for cyber network defense. Alerts generated by Intrusion Detection Sensors (IDSs) or Intrusion Prevention Sensors (IPSs) are fed into the data refinement (Level 0) and object assessment (L1) data fusion components. High-level situation/threat assessment (L2/L3) data fusion based on Markov game model and Hierarchical Entity Aggregation (HEA) are proposed to refine the primitive prediction generated by adaptive feature/pattern recognition and capture new unknown features. A Markov (Stochastic) game method is used to estimate the belief of each possible cyber attack pattern. Game theory captures the nature of cyber conflicts: determination of the attacking-force strategies is tightly coupled to determination of the defense-force strategies and vice versa. Also, Markov game theory deals with uncertainty and incompleteness of available information. A software tool is developed to demonstrate the performance of the high level information fusion for cyber network defense situation and a simulation example shows the enhanced understating of cyber-network defense.

An Adaptive Markov Game Model for Threat Intent Inference

In an adversarial military environment, it is important to efficiently and promptly predict the enemys tactical intent from lower level spatial and temporal information. In this paper, we propose a decentralized Markov game (MG) theoretic approach to estimate the belief of each possible enemy course of action (ECOA), which is utilized to model the adversary intents. It has the following advantages: (1) It is decentralized. Each cluster or team makes decisions mostly based on local information. We put more autonomies in each group allowing for more flexibilities; (2) A Markov decision process (MDP) can effectively model the uncertainties in the noisy military environment; (3) It is a game model with three players: red force (enemies), blue force (friendly forces), and white force (neutral objects); (4) Correlated-Q reinforcement learning is integrated. With the consideration that actual value functions are not normally known and they must be estimated, we integrate correlated-Q learning concept in our game approach to dynamically adjust the payoffs function of each player. A simulation software package has been developed to demonstrate the performance of our proposed algorithms. Simulations have verified that our proposed algorithms are scalable, stable, and satisfactory in performance.

Game-Theoretic Modeling and Control of Military Air Operations with Civilian Players

It is well known that civilians often play an active role in wars. That is, they are not just passively static but might purposefully take actions to help one side in a battle to minimize their losses or achieve some political purpose. Unfortunately, existing game theoretic models usually do not consider this situation, even though collateral damage has been considered in a paper on a two-player game model. In this paper, a three-player attrition-type discrete time dynamic game model is formulated, in which there are two opposing forces and one civilian player that might be either neutral or slightly biased. We model the objective functions, control strategies of different players, and identify the associated constraints on the control and state variables. Existing attrition-like state space models can be regarded as a special case of the model proposed in this paper. An example scenario and extensive simulations illustrate possible applications of this model, and comparative discussions further clarify the benefits.

Speech separation algorithms for multiple speaker environments

Conventional speaker identification and speech recognition algorithms do not perform well if there are multiple speakers in the background. For high performance speaker identification and speech recognition applications in multiple speaker environments, a speech separation stage is essential. Here we summarize the implementation of three speech separation techniques. Advantages and disadvantages of each method are highlighted, as no single method can work under all situations. Stand-alone software prototypes for these methods have been developed and evaluated.

Game-Theoretic Modeling and Control of Military Air Operations with Retaliatory Civilians

Non-neutral civilians often play an active role in wars. That is, they are not just passively static but might dynamically take non-neutral actions to retaliate against the Forces who create collateral damage for them. Unfortunately, existing game theoretic models usually do not consider this situation. In this paper, an attrition-type discrete time dynamic game model is formulated, in which two opposing forces fight under reactive civilian environments that might be either neutral or slightly biased. We model the objective functions, control strategies of different players, and identify the associated constraints on the control and state variables. Existing attrition-like state space models can be regarded as a special case of the model proposed in this paper. An example scenario and extensive simulations illustrate possible applications of this model and comparative discussions further clarify the benefits.

Analysis and visualization of large complex attack graphs for networks security

In this paper, we have proposed a comprehensive and innovative approach for analysis and visualization of large complex multi-step cyber attack graphs. As an automated tool for cyber attack detection, prediction, and visualization, the newly proposed method transforms large quantities of network security data into real-time actionable intelligence, which can be used to (1) provide guidance on network hardening to prevent attacks, (2) perform real-time attack event correlation during active attacks, and (3) formulate post-attack responses. We show that it is possible to visualize the complex graphs, including all possible network attack paths while still keeping complexity manageable. The proposed analysis and visualization tool provides an efficient and effective solution for predicting potential attacks upon observed intrusion evidence, as well as interactive multi-resolution views such that an analyst can first obtain high-level overviews quickly, and then drill down to specific details.

Enhanced speech in noisy multiple speaker environment

Noisy environments seriously degrade the performance of speech recognition systems. Here we implement a high performance speech enhancement algorithm. Data from speech separation challenge were used to evaluate the method. It was observed that the enhanced speech significantly improved the recognition performance. In 2 out of 4 SNR cases, over 100% relative percentage improvements were achieved. Standalone software prototype has been developed and evaluated.

An integrated approach to robust speaker identification and speech recognition

Conventional speaker identification and speech recognition algorithms cannot deal with noisy and multiple speaker environments. For example, IBM via Voice has low recognition rates if dictation is done in a noisy environment. In order to achieve high performance in speaker identification and speech recognition, we propose an integrated approach that takes every facet of the process into account. Here we summarize some preliminary results from the application of this integrated approach to robust speaker identification and speech recognition. A real-time stand-alone software prototype has been developed to evaluate the effectiveness of the approach.