Deception Detection

Conference Paper
External
Date of publication: 
Mon, 04/07/2011
Discovering and gathering information from multiple disparate sources, assessing the veracity of that information, and determining how and when to utilize the information in each stream is one of the most perplexing challenges that governments and businesses face. This symposium explores how governments and businesses can increase the fidelity and use of information streams. Assessing the credibility of information and increasing the quality of information streams is critical in many venues (e.g., law enforcement scenarios, border security, fraud investigations, intelligence gathering, etc.).
Article
External
Date of publication: 
Fri, 02/03/2012
Using video analyzed from a novel deception experiment, this paper introduces computer vision research in progress that addresses two critical components to computational modeling of deceptive behavior : 1) individual non verbal behavior differences, and 2) deceptive ground truth. Video interviews analyzed for this research were participants recruited as potential hooligans (extreme sports fans) who lied about support for their rival team. From these participants, we will process and extract features representing their faces that will be submitted to slow feature analysis. From this analysis we will identify each person’s unique facial expression and behaviors, and look for systemic variation between truth and deception.
Article
External
Date of publication: 
Tue, 11/10/2011
Deception detection remains novel, challenging, and important in natural language processing, machine learning, and the broader LIS community. Computational tools capable of alerting users to potentially deceptive content in computer-mediated messages are invaluable for supporting undisrupted, computer-mediated communication, information seeking, credibility assessment and decision making. The goal of this ongoing research is to inform creation of such automated capabilities.
Conference Paper
External
Date of publication: 
Fri, 05/08/2005
This article presents a Group decision support systems (GDSS) framework for deception detection based on collaborative process patterns, thinkLets. The focus of research is on designing group processes to aid deception detection from various information sources such as text transcripts, video clips, and audio clips. Architecture of a prototype under development based on the proposed framework is outlined
Article
External
Date of publication: 
Wed, 26/05/2010
Conference Paper
External
Date of publication: 
Wed, 13/03/2013
Contact: 
Judee Burgoon, Mark Adkins, John Kruse, Matthew L. Jensen, Thomas Meservy, Douglas P. Twitchell, Amit Deokar, Jay F. Nunamaker Center for the Management of Information University of Arizona jburgoon@cmi.arizona.edu Shan Lu, Gabriel Tsechpenakis, Dimitris N. Metaxas Center of Computational Biomedicine Imaging and Modeling Rutgers University shanlu@cs.rutgers.edu Robert E. Younger Space and Naval Warfare Systems Center younger@spawar.navy.mil

 

Past research in deception detection at the University of Arizona has guided the investigation of intent detection. A theoretical foundation and model for the analysis of intent detection is proposed. Available test beds for intent analysis are discussed and two proof-ofconcept studies exploring nonverbal communication within the context of deception detection and intent analysis are shared
Report
External
Date of publication: 
Wed, 20/09/2017
Contact: 
UK Home Office, 2007

Immigration Officers work in a highly pressured and complex environment, and their decisions

about whether or not to hold a passenger for further questioning draw on a range of information, intelligence and personal judgments. Within this complex process, one important factor identified by IOs is economic credibility, which relates both the situation in the passenger’s home country and the circumstances of the individual passenger. 

Corruption persists at Customs and Border Protection

A report from the United States Government Accountability Office concluded that additional actions are needed to strengthen CBP efforts to mitigate risk of employee corruption and misconduct. Since 2005 a total of 144 current or former CBP employees were arrested or indicted for corruption-related activities, such as the smuggling of aliens and drugs, of whom 125 have been convicted as of October 2012. Further, the majority of allegations occurred at locations along the southwest border. The GAO suggests improvements to CBP staff screening processes and recommends giving consideration to the expansion of the Agency poligraph programme.
Article
Internal
Date of publication: 
Wed, 20/09/2017
Contact: 
Monica Gariup

Published on Border post - October 2012