King's College London

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