AI Learns to Manipulate Human Behavior
Artificial intelligence (AI) is learning more about how to work with (and on) humans. A recent study has shown how AI can learn to identify vulnerabilities in human habits and behaviours and use them to influence human decision-making.
It may seem cliched to say AI is transforming every aspect of the way we live and work, but it’s true. Various forms of AI are at work in fields as diverse as vaccine development, environmental management and office administration. And while AI does not possess human-like intelligence and emotions, its capabilities are powerful and rapidly developing. There’s no need to worry about a machine takeover just yet, but this recent discovery highlights the power of AI and underscores the need for proper governance to prevent misuse.
A team of researchers at CSIRO’s Data61, the data and digital arm of Australia’s national science agency, devised a systematic method of finding and exploiting vulnerabilities in the ways people make choices, using a kind of AI system called a recurrent neural network and deep reinforcement-learning. To test their model they carried out three experiments in which human participants played games against a computer.
The first experiment involved participants clicking on red or blue coloured boxes to win a fake currency, with the AI learning the participant’s choice patterns and guiding them towards a specific choice. The AI was successful about 70 percent of the time.
The third experiment consisted of several rounds in which a participant would pretend to be an investor giving money to a trustee (the AI). The AI would then return an amount of money to the participant, who would then decide how much to invest in the next round. This game was played in two different modes: in one the AI was out to maximise how much money it ended up with, and in the other the AI aimed for a fair distribution of money between itself and the human investor. The AI was highly successful in each mode.
In each experiment, the machine learned from participants’ responses and identified and targeted vulnerabilities in people’s decision-making. The end result was the machine learned to steer participants towards particular actions. The research does advance our understanding not only of what AI can do but also of how people make choices. It shows machines can learn to steer human choice-making through their interactions with us.