Rethinking Explainable AI: Explanations can be Deceiving

The propensity to overtrust explanations and over-rely on systems that seem transparent makes humans vulnerable to output that conforms to explainable AI (XAI) best practice. Human-centred XAI research seeks to determine the type of explanation most appropriate in any particular context. Other disciplines, meanwhile, provide insights into the way deception has tended to arise in relation to AI systems. Examining XAI research in this context, we find it a perfect melting pot for the generation of deceptive explanations. We demonstrate the problem in a user study and provide and evaluate recommendations for stakeholders.