A Deliberate BIAT Logic for Modeling Manipulations
Résumé
In many applications, selfish, dishonest or malicious agents may find an interest in manipulating others. While many works deal with designing robust systems, few works deal with logical reasoning about manipulation. Based on social science literature, we propose a new logical framework to express and reason about manipulation , defined as a deliberate effect to instrumentalize a victim while making sure to conceal that instrumentalization. Since manipulation relies on deliberate effects of a manipulator, we propose a new BIAT operator to catch deliberate effects. We first prove that this logical framework is sound and complete. Then we formally define manipulation and we show our logical framework also expresses related notions such as coercion, persuasion, or deception.
Domaines
Intelligence artificielle [cs.AI]
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...