Deception

Stefan Sarkadi

doi:10.24963/ijcai.2018/834

Deception

Stefan Sarkadi

Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

319 Downloads (Pure)

Abstract

Recent events that revolve around fake news indicate
that humans are more susceptible than ever
to mental manipulation by powerful technological
tools. In the future these tools may become autonomous.
One crucial property of autonomous
agents is their potential ability to deceive. From
this research we hope to understand the potential
risks and benefits of deceptive artificial agents. The
method we propose to study deceptive agents is by
making them interact with agents that detect deception
and analyse what emerges from these interactions
given multiple setups such as formalisations
of scenarios inspired from historical cases of deception

Original language	English
Title of host publication	Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Publisher	IJCAI-INT JOINT CONF ARTIF INTELL
Pages	5781-5782
Number of pages	2
DOIs	https://doi.org/10.24963/ijcai.2018/834
Publication status	Published - 2018

Access to Document

10.24963/ijcai.2018/834

Deception (Extended Abstract)Final published version, 56.2 KB

https://www.ijcai.org/proceedings/2018/834

Modelling Deception using Theory of Mind in Multi-Agent Systems
Sarkadi, S., Panisson, A. R., Bordini, R. H., McBurney, P. J., Parsons, S. D. & Chapman, M. D., 2019, In: AI COMMUNICATIONS. 32, 4, p. 287-302 16 p.
Research output: Contribution to journal › Article › peer-review

Open Access
File
43 Citations (Scopus)

811 Downloads (Pure)
On the Formal Semantics of Theory of Mind in Agent Communication
Panisson, A. R., Sarkadi, S., McBurney, P. J., Parsons, S. D. & Bordini, R. H., 6 Dec 2018, Proceedings of the 6th International Conference on Agreement Technologies: co-located with EUMAS 2018. 15 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Open Access
File
Towards an Approach for Modelling Uncertain Theory of Mind in Multi-Agent Systems
Sarkadi, S., Panisson, A. R., Bordini, R. H., McBurney, P. J. & Parsons, S. D., 6 Dec 2018, Proceedings of the 6th International Conference on Agreement Technologies: co-located with EUMAS 2018. 15 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Open Access
File

Cite this

@inbook{c43ee2d980db4861834780bfe45e9de3,

title = "Deception",

abstract = "Recent events that revolve around fake news indicate that humans are more susceptible than ever to mental manipulation by powerful technological tools. In the future these tools may become autonomous. One crucial property of autonomous agents is their potential ability to deceive. From this research we hope to understand the potential risks and benefits of deceptive artificial agents. The method we propose to study deceptive agents is by making them interact with agents that detect deception and analyse what emerges from these interactions given multiple setups such as formalisations of scenarios inspired from historical cases of deception",

author = "Stefan Sarkadi",

year = "2018",

doi = "10.24963/ijcai.2018/834",

language = "English",

pages = "5781--5782",

booktitle = "Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence",

publisher = "IJCAI-INT JOINT CONF ARTIF INTELL",

}

TY - CHAP

T1 - Deception

AU - Sarkadi, Stefan

PY - 2018

Y1 - 2018

N2 - Recent events that revolve around fake news indicate that humans are more susceptible than ever to mental manipulation by powerful technological tools. In the future these tools may become autonomous. One crucial property of autonomous agents is their potential ability to deceive. From this research we hope to understand the potential risks and benefits of deceptive artificial agents. The method we propose to study deceptive agents is by making them interact with agents that detect deception and analyse what emerges from these interactions given multiple setups such as formalisations of scenarios inspired from historical cases of deception

AB - Recent events that revolve around fake news indicate that humans are more susceptible than ever to mental manipulation by powerful technological tools. In the future these tools may become autonomous. One crucial property of autonomous agents is their potential ability to deceive. From this research we hope to understand the potential risks and benefits of deceptive artificial agents. The method we propose to study deceptive agents is by making them interact with agents that detect deception and analyse what emerges from these interactions given multiple setups such as formalisations of scenarios inspired from historical cases of deception

U2 - 10.24963/ijcai.2018/834

DO - 10.24963/ijcai.2018/834

M3 - Conference paper

SP - 5781

EP - 5782

BT - Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

PB - IJCAI-INT JOINT CONF ARTIF INTELL

ER -

Deception

Abstract

Access to Document

Fingerprint

Research output

Modelling Deception using Theory of Mind in Multi-Agent Systems

On the Formal Semantics of Theory of Mind in Agent Communication

Towards an Approach for Modelling Uncertain Theory of Mind in Multi-Agent Systems

Cite this