Intent Driven Adversarial Modeling

Abstract

Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. AbstractModern elements of military intelligence and decision making require predictions of adversary force actions and reactions to provide a complete and realistic viewpoint. Current methods for providing realistic adversary force simulation are largely manual processes. Adversarial simulation requires continual assessment of friendly courses of action and is currently "human assessment capability" limited. To develop a computational model of dynamic adversary behaviors that includes the ability to integrate with intelligence and mission data sources, computational models must address operational patterns, behaviors, or doctrines of present-day adversaries (terrorist cells, local insurgents, guerillas, and armed thugs) as well as more conventional force elements. The dynamic nature of adversary force behavior with respect to the changing capabilities, biases, beliefs, goals, intentions, and perceptions of friendly force actions must be addressed. The Emergent Adversarial Modeling System (EAMS) addresses these elements through explicit focus on adversarial intent as a driver for adversarial response. Specific capabilities address the changing nature of adversary composition. This paper will discuss the results of the ongoing EAMS research project into adversarial modeling and adversarial response simulation.

Replication of human operators’ situation assessment and decision making for simulated area reconnaissance in wargames

“…Adversarial intent is an important component in threat assessment and a challenge research area. Using Bayesian networks, Gilmour et al 17 proposed a model of adversarial intent to describe the influence of an adversary's beliefs on behavior and the possible relationships between an adversary's goals and the actions chosen to realize those goals. To predict an enemy's tactical intention, Johansson and Falkman 18,19 explored a Bayesian approach based on protection values, target type, weapon type, distance, and direction.…”

Asynchronous Chess: A Real-Time, Adversarial Research Environment

“…Such activities may include predicting and evaluating enemy courses of action (eCOAs) [5,4], competing against arbitrary opponents in adversarial gaming environments such as robotic soccer [8], protecting computer networks against everchanging malicious attacks [9], and finding appropriate partners to cooperate with-as well as those to avoid-when forming coalitions [14,13]. Increasingly, such activities are being examined in the context of dynamic multi-agent systems (MASs), where the state of the world is changing as the agents operate.…”

“…Other efforts have considered real-time competitions in the context of simulated markets [22,15] and robotic software [8,20]. Similarly, there is current research in adversarial modeling to support military mission planning [5,4] and coalition formation [14,13]. But AChess is the first research environment that combines real-time decision making and adversarial reasoning in a problem domain that allows researchers to focus on just these core issues.…”

“…Similarly, in the areas of military mission planning and cyberwarfare, systems such as the Emergent Adversarial Modeling System (EAMS) [5,4] and MITRE's simulated cyberwarfare environment [9], allow users to explore various avenues for dealing with adversarial tactics. These environments support the study of automated scenario generation and dynamic update, intelligent adversarial behavior modeling, effects-based/attrition-based behavior modeling, and real-time analysis technology for comparing and grading effectiveness of alternative simulations.…”