Using game theory with intrinsic motivation to examine anti-hacking policies for autonomous systems

  title={Using game theory with intrinsic motivation to examine anti-hacking policies for autonomous systems},
  author={Kathryn E. Merrick and Medria K. D. Hardhienata and Kamran Shafi and Jiankun Hu},
  journal={2016 IEEE Symposium Series on Computational Intelligence (SSCI)},
With the increasing excitement about the emergence of autonomous systems, there is also a level of caution associated with the possible vulnerabilities of such systems. As systems become more independent, it may become more difficult for humans to trust them, particularly in settings where they may be vulnerable to malicious behavior by others. This paper presents a game theoretic model for autonomous systems subject to hacking. We propose a hacking game that models the interaction between an… 

Figures and Tables from this paper


A Survey of Game Theoretic Approaches to Modelling Decision-Making in Information Warfare Scenarios
A systematic identification and classification of information warfare games, as a basis for modelling decision-making by humans and machines in information warfare scenarios, and a taxonomy of games that map to information warfare and cyber crime problems as a precursor to future research on decision- making in such scenarios.
The Role of Implicit Motives in Strategic Decision-Making: Computational Models of Motivated Learning and the Evolution of Motivated Agents
Two agent-based computational models of power-, achievement- and affiliation-motivated individuals engaged in game-play are presented and it is demonstrated that misperception, when it is a result of motivation, causes agents with different motives to play a given game differently.
A game theoretic framework for incentive-based models of intrinsic motivation in artificial systems
This paper uses agent-based simulations to demonstrate that players with different optimally motivating incentive act differently as a result of their altered perception of the game, and discusses the implications both for modeling human behavior and for designing artificial agents or robots.
Modelling Information Warfare as a Game
Four example games which illustrate the different requirements for an effective playing strategy in information warfare are presented and meta-strategies whose goal is to modify the perceived costs and conditions of a game are described.
Culture jamming: from activism to hactivism
A new kind of Internet threat has emerged. Hacking is increasingly being used as a weapon by individuals to promote their political ideologies by engaging in distributed citizen-based warfare. Their
Learning Through Reinforcement and Replicator Dynamics
A version of Bush and Mosteller's stochastic learning theory in the context of games is considered and it is shown that in the continuous time limit the biological model coincides with the deterministic, continuous time replicator process.
The Challenge of Autonomous Lethal Robotics to International Humanitarian Law
The concept of a truly autonomous weapons system--a system which is capable of operating itself, independently from human oversight--sounds more like science fiction than science fact. However, the
Information Warfare
A useful model must be based on consistent first principles and formal structured analysis so that the result can be shared, evaluated and used to support the development of war-fighting techniques in the Information Age.
Information Warfare: Time for a redefinition.
There is a need to shift the emphasis from many of the military underpinnings to its relevance in modern society and the challenges in the commercial environment to make information warfare relevant to today's generation of students.
Cyber warfare: Issues and challenges