We present a framework for describing insiders and their actions based on the organization, the environment, the system, and the individual. Using several real examples of unwelcome insider action (hard drive removal, stolen intellectual property, tax fraud, and proliferation of e-mail responses), we show how the taxonomy helps in understanding how each situation arose and could have been addressed. The differentiation among types of threats suggests how effective responses to insider threats might be shaped, what choices exist for each type of threat, and the implications of each. Future work will consider appropriate strategies to address each type of insider threat in terms of detection, prevention, mitigation, remediation, and punishment.

In this paper, an algorithm is developed for collaboratively training networks of kernel-linear least-squares regression estimators. The algorithm is shown to distributively solve a relaxation of the classical centralized least-squares regression problem. A statistical analysis shows that the generalization error afforded agents by the collaborative training algorithm can be bounded in terms of the relationship between the network topology and the representational capacity of the relevant reproducing kernel Hilbert space. Numerical experiments suggest that the algorithm is effective at reducing noise. The algorithm is relevant to the problem of distributed learning in wireless sensor networks by virtue of its exploitation of local communication. Several new questions for statistical learning theory are proposed.

This paper provides self-contained proof of a theorem relating probabilistic coherence of forecasts to their non-domination by rival forecasts with respect to any proper scoring rule. The theorem recapitulates insights achieved by other investigators, and clarifies the connection of coherence and proper scoring rules to Bregman divergence.

In this paper, computational aspects of the panel aggregation problem are addressed. Motivated primarily by applications of risk assessment, an algorithm is developed for fusing large corpora of internally incoherent probability assessments. The algorithm is characterized by a provable performance guarantee, and is demonstrated to be orders of magnitude faster than existing tools when tested on several real-world data-sets. In addition, unexpected connections between research in risk assessment and wireless sensor networks are exposed, as several key ideas are illustrated to be useful in both fields

This paper addresses the problem of distributed learning under communication constraints, motivated by distributed signal processing in wireless sensor networks and data mining with distributed databases. After formalizing a general model for distributed learning, an algorithm for collaboratively training regularized kernel least-squares regression estimators is derived. Noting that the algorithm can be viewed as an application of successive orthogonal projection algorithms, its convergence properties are investigated and the statistical behavior of the estimator is discussed in a simplified theoretical setting.

Motivated by sensor networks and other distributed settings, several models for distributed learning are presented. The models differ from classical works in statistical pattern recognition by allocating observations of an independent and identically distributed (i.i.d.) sampling process among members of a network of simple learning agents. The agents are limited in their ability to communicate to a central fusion center and thus, the amount of information available for use in classification or regression is constrained. For several basic communication models in both the binary classification and regression frameworks, we question the existence of agent decision rules and fusion rules that result in a universally consistent ensemble; the answers to this question present new issues to consider with regard to universal consistency. This paper addresses the issue of whether or not the guarantees provided by Stone's theorem in centralized environments hold in distributed settings.

Motivated by sensor networks and traditional methods of statistical pattern recognition, a model for distributed learning is formulated. The model is in line with learning models considered in the context of Stone-type classifiers, but differs in the dependency structure of the sampling process; questions of universal consistency are addressed.