Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deception Analysis with Artificial Intelligence: An Interdisciplinary Perspective

Stefan Sarkadi

TL;DR

Deception in hybrid human–AI ecosystems threatens trust and societal functioning, motivating the development of a holistic framework. DAMAS integrates multi-agent systems (MAS) and agent-based modelling (ABM) with Intelligence Analysis methods to model, explain, and analyze deception across interaction and population levels. The framework emphasizes Theory of Mind, non-cue-based deception theories (IMT2, IDT, TDT), and hybrid argumentation for explanations, aiming to provide scalable, explainable tools to support policy and regulation. If realized, DAMAS could bridge AI research and deception analysis, enabling counter-deception insights, IBE-driven explanations, and safer deployment of deceptive AI under robust ethical guidelines.

Abstract

Humans and machines interact more frequently than ever and our societies are becoming increasingly hybrid. A consequence of this hybridisation is the degradation of societal trust due to the prevalence of AI-enabled deception. Yet, despite our understanding of the role of trust in AI in the recent years, we still do not have a computational theory to be able to fully understand and explain the role deception plays in this context. This is a problem because while our ability to explain deception in hybrid societies is delayed, the design of AI agents may keep advancing towards fully autonomous deceptive machines, which would pose new challenges to dealing with deception. In this paper we build a timely and meaningful interdisciplinary perspective on deceptive AI and reinforce a 20 year old socio-cognitive perspective on trust and deception, by proposing the development of DAMAS -- a holistic Multi-Agent Systems (MAS) framework for the socio-cognitive modelling and analysis of deception. In a nutshell this paper covers the topic of modelling and explaining deception using AI approaches from the perspectives of Computer Science, Philosophy, Psychology, Ethics, and Intelligence Analysis.

Deception Analysis with Artificial Intelligence: An Interdisciplinary Perspective

TL;DR

Deception in hybrid human–AI ecosystems threatens trust and societal functioning, motivating the development of a holistic framework. DAMAS integrates multi-agent systems (MAS) and agent-based modelling (ABM) with Intelligence Analysis methods to model, explain, and analyze deception across interaction and population levels. The framework emphasizes Theory of Mind, non-cue-based deception theories (IMT2, IDT, TDT), and hybrid argumentation for explanations, aiming to provide scalable, explainable tools to support policy and regulation. If realized, DAMAS could bridge AI research and deception analysis, enabling counter-deception insights, IBE-driven explanations, and safer deployment of deceptive AI under robust ethical guidelines.

Abstract

Humans and machines interact more frequently than ever and our societies are becoming increasingly hybrid. A consequence of this hybridisation is the degradation of societal trust due to the prevalence of AI-enabled deception. Yet, despite our understanding of the role of trust in AI in the recent years, we still do not have a computational theory to be able to fully understand and explain the role deception plays in this context. This is a problem because while our ability to explain deception in hybrid societies is delayed, the design of AI agents may keep advancing towards fully autonomous deceptive machines, which would pose new challenges to dealing with deception. In this paper we build a timely and meaningful interdisciplinary perspective on deceptive AI and reinforce a 20 year old socio-cognitive perspective on trust and deception, by proposing the development of DAMAS -- a holistic Multi-Agent Systems (MAS) framework for the socio-cognitive modelling and analysis of deception. In a nutshell this paper covers the topic of modelling and explaining deception using AI approaches from the perspectives of Computer Science, Philosophy, Psychology, Ethics, and Intelligence Analysis.
Paper Structure (27 sections, 2 figures, 2 tables)

This paper contains 27 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Theories and Components of Deception
  3. Philosophical Perspectives
  4. Socio-Cognitive Perspectives
  5. Reductionism & Previous Research in Deceptive AI
  6. Multi-Agent Frameworks vs AI Reductionism
  7. Previous Work
  8. Deception in Agent Societies
  9. Logical Aspects of Agent Deception
  10. Strategies for Agent Deception
  11. Reasoning in Agent Deception
  12. Engineering Deceptive Agents
  13. Embodied Deceptive Agents
  14. DAMAS: A MAS Framework for Deception Analysis
  15. Modelling Deception
  16. ...and 12 more sections

Figures (2)

  • Figure 1: Number of publications with respective terms in the title and abstract categorised in the field of AI from 2000 until 2022. The search engine for publications used is www.dimensions.ai, the area of research used to filter results was '0801 Artificial Intelligence and Image Processing'. Chart was printed on 13th January 2022.
  • Figure 2: DAMAS would act as a bridge between AI expertise and the methods used in intelligence analysis to explain deception holistically using IBE.