These experts are racing to protect AI from hackers. Time is running out


Image Recognition

ARTICLE SOURCE

"The benefits are real, but we have to do it with our eyes open -- there are risks and we have to defend our AI systems." Right now, the amount of adversarial AI in practice is very small but we don't think it will be in future, he says. Building platforms and tools to assess and protect AI systems against the threats of today is difficult enough. These AI systems are trained on millions of images found on the internet and can produce new images based on many genres. But as cyber defenses get better, we're starting to see more of the AI attacks," says DARPA's Draper.