Conference paper by Dieter Vanderelst and Alan Winfield.
Presented at the AIES 2018 conference.
Concerns over the risks associated with advances in Artificial Intelligence have prompted calls for greater efforts toward robust and beneficial AI, including machine ethics. Recently, roboticists have responded by initiating the development of so-called ethical robots. These robots would, ideally, evaluate the consequences of their actions and morally justify their choices.
This emerging field promises to develop extensively over the next years. However, in this paper, we point out an inherent limitation of the emerging field of ethical robots. We show that building ethical robots also inevitably enables the construction of unethical robots. In three experiments, we show that it is remarkably easy to modify an ethical robot so that it behaves competitively, or even aggressively. The reason for this is that the cognitive machinery required to make an ethical robot can always be corrupted to make unethical robots. We discuss the implications of this finding to the governance of ethical robots. We conclude that the risks that a robot’s ethics might be compromised by unscrupulous actors are so great as to raise serious doubts over the wisdom of embedding ethical decision making in real-world safety critical robots, such as driverless cars.