Deqing Li

Intent-Driven Insider Threat Detection in Intelligence Analyses

When decisions need to be made in government, the intelligence community (IC) is tasked with analyzing the situation. This analysis is based on a huge amount of information and usually under severe time constraints. As such, it is particularly vulnerable to attacks from insiders with malicious intent. A malicious insider may alter, fabricate, or hide critical information in their analytical products, such as reports, in order to interfere with the decision making process. In this paper, we focus on detecting such malicious insiders. Malicious actions such as disinformation tend to be very subtle and thus difficult to detect. Therefore, we employ a user modeling technique to model an insider based on logged information and documents accessed while accomplishing an intelligence analysis task. We create a computational model for each insider and apply several detection metrics to analyze this model as it changes over time. If any deviation of behavior is detected, alerts can be issued. A pilot test revealed that the computed deviations had a high correlation with insiderspsila cognitive styles. Based on this finding, we designed a framework that minimized the impact of differences in cognitive styles. In our evaluation, we used data collected from intelligence analysts, and simulated malicious insiders based on this data. A high percentage of the simulated malicious insiders were successfully detected.

Modeling complex social scenarios using Culturally Infused Social Networks

Modeling complex real world scenarios require representing and analyzing information from multiple domains including social, economic and political aspects. However, most of the current frameworks in social networks are not generic enough to incorporate multi-domain information or to be applied in different scenarios. Current frameworks also make simplifications in other modeling aspects such as incorporating dynamism and providing multi-scale analyses. Representing culture is critical to truly capture the nuances of various social processes. It also helps to make the framework generic enough to be applied in multiple application domains.We will leverage a novel framework called the Culturally Infused Social Network (CISN) to represent culture using probabilistic reasoning networks called Bayesian Knowledge Bases (BKBs), in representations known as cultural fragments. Cultural fragments model the intent of actors by relating their actions to underlying beliefs and goals. CISN also supports analysis algorithms to make predictions and provide explanations. We validate CISN by simulating the 2006 Somali conflict involving the Islamic Court Union (ICU). The Somali conflict is a complex scenario requiring deep understanding of myriad factors. We focus on analyzing the group stability of ICU, how changing alliance caused conflicts and led to its ultimate demise. We define a metric to measure instability in a group, identify critical factors that led to instability in ICU and provide analyses.

Adversarial intent modeling using embedded simulation and temporal Bayesian knowledge bases

To foster shared battlespace awareness among air strategy planners, BAE Systems has developed Commanders Model Integration and Simulation Toolkit (CMIST), an Integrated Development Environment for authoring, integration, validation, and debugging of models relating multiple domains, including political, military, social, economic and information. CMIST provides a unified graphical user interface for such systems of systems modeling, spanning several disparate modeling paradigms. Here, we briefly review the CMIST architecture and then compare modeling results using two approaches to intent modeling. The first uses reactive agents with simplified behavior models that apply rule-based triggers to initiate actions based solely on observations of the external world at the current time in the simulation. The second method models proactive agents running an embedded CMIST simulation representing their projection of how events may unfold in the future in order to take early preventative action. Finally, we discuss a recent extension to CMIST that incorporates Temporal Bayesian Knowledge Bases for more sophisticated models of adversarial intent that are capable of inferring goals and future actions given evidence of current actions at particular times.

Computational Deception and Noncooperation

Many applications require knowledge about how to deceive, including those related to safety, security, and warfare. Speech and text analysis can help detect deception, as can cameras, microphones, physiological sensors, and intelligent software. Models of deception and noncooperation can make a virtual or mixed-reality training environment more realistic, improve immersion, and thus make it more suitable for training military or security personnel. Robots might need to operate in physical and nontraining environments where they must perform military activity, including misleading the enemy. The contributions to this installment of Trends & Controversies present state-of-the-art research approaches to the analysis and generation of noncooperative and deceptive behavior in virtual humans, agents, and robots; the analysis of multiparty interaction in the context of deceptive behavior; and methods to detect misleading information in texts and computer-mediated communication. Articles include: "Computational Deception and Noncooperation," by Anton Nijholt; "Robots that Need to Mislead: Biologically-Inspired Machine Deception," by Ronald C. Arkin; "Deception in Sports Using Immersive Environments," by Sébastien Brault, Richard Kulpa, Franck Multon, and Benoit Bideau; "Non-Cooperative and Deceptive Virtual Agents," by David Traum; "Deception Detection in Multiparty Contexts,"by Hayley Hung; "Deception Detection, Human Reasoning, and Deception Intent," by Eugene Santos Jr., Deqing Li, and Fei Yu; and "Automatic Deception Detection in Computer-Mediated Communication," by Lina Zhou and Dongsong Zhang.We discuss the importance of modelling deceptive and noncooperative behavior in computer sytems such as intelligent agents, robots and serious game environments for traing and simulation. This short survey is an introduction to the next six contributions to this installment of Trends & Controversies, we find state-of-the-art research approaches to the analysis and generation of noncooperative and deceptive behavior in virtual humans, agents, and robots; the analysis of multiparty interaction in the context of deceptive behavior; and methods to detect misleading information in texts and computer-mediated communication.

Capturing User Intent for Analytic Process

We are working on the problem of modeling an analysts intent in order to improve collaboration among intelligence analysts. Our approach is to infer the analysts goals, commitment, and actions to improve the effectiveness of collaboration. This is a crucial problem to ensure successful collaboration because analyst intent provides a deeper understanding of what analysts are trying to achieve and how they are achieving their goals than simply modeling their interests. The novelty of our approach relies on modeling the process of committing to a goal as opposed to simply modeling topical interests. Additionally, we dynamically generate a goal hierarchy by exploring the relationships between concepts related to a goal. In this short paper, we present the formal framework of our intent model, and demonstrate how it is used to detect the common goals between analysts using the APEX dataset.

Temporal Bayesian Knowledge Bases - Reasoning about uncertainty with temporal constraints

Time is ubiquitous. Accounting for time and its interaction with change is crucial to modeling the dynamic world, especially in domains whose study of data is sensitive to time such as in medical diagnosis, financial investment, and natural language processing, to name a few. We present a framework that incorporates both uncertainty and time in its reasoning scheme. It is based on an existing knowledge representation called Bayesian Knowledge Bases. It provides a graphical representation of knowledge, time and uncertainty, and enables probabilistic and temporal inferencing. The reasoning scheme is probabilistically sound and the fusion of temporal fragments is well defined. We will discuss some properties of this framework and introduce algorithms to ensure groundedness during the construction of the model. The framework has been applied to both artificial and real world scenarios.

An extensive spectroscopic time series of three Wolf–Rayet stars – I. The lifetime of large-scale structures in the wind of WR 134

During the summer of 2013, a 4-month spectroscopic campaign took place to observe the variabilities in three Wolf-Rayet stars. The spectroscopic data have been analyzed for WR 134 (WN6b), to better understand its behaviour and long-term periodicity, which we interpret as arising from corotating interaction regions (CIRs) in the wind. By analyzing the variability of the He II

Deception detection in human reasoning

\lambda

Impacts of Analysts' Cognitive Styles on the Analytic Process

5411 emission line, the previously identified period was refined to P = 2.255

Incorporating Social Theories in Computational Behavioral Models

\pm