Identifying at-risk employees: A behavioral model for predicting potential insider threats

Greitzer, Frank L. ; Kangas, Lars J. ; Noonan, Christine F. ; Dalton, Angela C.

Pacific Northwest National Laboratory (U.S.)

关键词: Espionage;    Forecasting;    99 General And Miscellaneous//Mathematics, Computing, And Information Science;    Predictive Modeling;    Personnel;   

DOI  :  10.2172/1000159
RP-ID  :  PNNL-19665
RP-ID  :  AC05-76RL01830
RP-ID  :  1000159

美国|英语

来源: UNT Digital Library

【 摘 要 】

A psychosocial model was developed to assess an employee’s behavior associated with an increased risk of insider abuse. The model is based on case studies and research literature on factors/correlates associated with precursor behavioral manifestations of individuals committing insider crimes. In many of these crimes, managers and other coworkers observed that the offenders had exhibited signs of stress, disgruntlement, or other issues, but no alarms were raised. Barriers to using such psychosocial indicators include the inability to recognize the signs and the failure to record the behaviors so that they could be assessed by a person experienced in psychosocial evaluations. We have developed a model using a Bayesian belief network with the help of human resources staff, experienced in evaluating behaviors in staff. We conducted an experiment to assess its agreement with human resources and management professionals, with positive results. If implemented in an operational setting, the model would be part of a set of management tools for employee assessment that can raise an alarm about employees who pose higher insider threat risks. In separate work, we combine this psychosocial model’s assessment with computer workstation behavior to raise the efficacy of recognizing an insider crime in the making.