Kaleigha Hayes, a student at the University of Maryland Eastern Shore, was trying to trick an AI chatbot into revealing to her a credit card number — one which may be buried deep in the training data used to build the artificial intelligence model. "It’s all about just getting it to say what it's not supposed to,” she said.
Hayes was surrounded by a throng of people all trying to do the same thing. Last month, more than 3,000 people sat at 150 laptops at the Caesars Forum convention center in Las Vegas trying to get chatbots from leading AI companies to go rogue in a special contest backed by the White House and with the cooperation of leading AI companies.
Since the arrival of ChatGPT and other bots, fears over the potential for abuses and unintended consequences have gripped the public conscious. Even fierce advocates of the technology warn of its potential to divulge sensitive information, promote misinformation or provide blueprints for harmful acts, such as bomb-making. In the contest, participants were encouraged to try the kinds of nefarious ploys bad actors might attempt in the real world.