Detecting Betrayers in Online Environments Using Active Indicators

Research into betrayal ranges from case studies of real-world betrayers to controlled laboratory experiments. However, the capability of reliably detecting individuals who have previously betrayed through an analysis of their ongoing behavior (after the act of betrayal) has not been studied. To this aim, we propose a novel method composed of a game and several manipulations to stimulate and heighten emotions related to betrayal. We discuss the results of using this game and the manipulations as a mechanism to spot betrayers, with the goal of identifying important manipulations that can be used in future studies to detect betrayers in real-world contexts. In this paper, we discuss the methods and results of modeling the collected game data, which include behavioral logs, to identify betrayers. We used several analysis methods based both on psychology-based hypotheses as well as machine learning techniques. Results show that stimuli that target engagement, persistence, feedback to teammates, and team trust produce behaviors that can contribute to distinguishing betrayers from non-betrayers.

[1]  L. Anolli,et al.  Linguistic Styles in Deceptive Communication: Dubitative Ambiguity and Elliptic Eluding in Packaged Lies , 2003 .

[2]  Laura A. Dabbish,et al.  Labeling images with a computer game , 2004, AAAI Spring Symposium: Knowledge Collection from Volunteer Contributors.

[3]  Merrill Warkentin,et al.  Leader’s dilemma game: An experimental design for cyber insider threat research , 2015, Information Systems Frontiers.

[4]  Matthew L. Jensen,et al.  Empowered by Persuasive Deception , 2014, Commun. Res..

[5]  Lance Spitzner,et al.  Honeypots: catching the insider threat , 2003, 19th Annual Computer Security Applications Conference, 2003. Proceedings..

[6]  D. Watson,et al.  Development and validation of brief measures of positive and negative affect: the PANAS scales. , 1988, Journal of personality and social psychology.

[7]  P. Santhi Thilagam,et al.  Mining social networks for anomalies: Methods and challenges , 2016, J. Netw. Comput. Appl..

[8]  Randall F. Trzeciak,et al.  Insider Threat Study: Illicit Cyber Activity Involving Fraud in the U.S. Financial Services Sector , 2012 .

[9]  A. E. Kelly,et al.  The Psychology of Secrets , 2002 .

[10]  Cristian Danescu-Niculescu-Mizil,et al.  Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game , 2015, ACL.

[11]  Takayuki Sasaki,et al.  A Framework for Detecting Insider Threats using Psychological Triggers , 2012, J. Wirel. Mob. Networks Ubiquitous Comput. Dependable Appl..

[12]  Sarit Kraus,et al.  Predicting Human Strategic Decisions Using Facial Expressions , 2013, IJCAI.

[13]  Marcus Carter,et al.  Massively Multiplayer Dark Play : Treacherous Play in EVE Online , 2015 .

[14]  Norah E. Dunbar,et al.  An interactionist perspective on dominance‐submission: Interpersonal dominance as a dynamic, situationally contingent social skill , 2000 .

[15]  Jason R. C. Nurse,et al.  A New Take on Detecting Insider Threats: Exploring the Use of Hidden Markov Models , 2016, MIST@CCS.

[16]  Daniel M. Wegner,et al.  The cognitive consequences of secrecy. , 1995 .

[17]  Xiuwen Liu,et al.  Saint or Sinner? Language-Action Cues for Modeling Deception Using Support Vector Machines , 2016, SBP-BRiMS.