Since the introduction of the Turing Test to measure machine intelligence, more and more sophisticated artificial systems have been developed to pass the test. These systems revealed some limitations of the Turing Test and new versions of the test have been developed over time in an attempt to overcome these shortcomings. Yet, all these variants still rely on the subjective judgments of human interrogators which are subject to biases. Here, we propose the brain-based Turing Test, a novel version of the test that uses implicit information encoded in the human brain to discriminate between human and artificial agents. We highlight multiple benefits of the brain-based Turing Test, outline its possible outcomes, present an empirical test using robot and human interactive communication, and explain how research in human-robot interaction can profit from it.
