The Next Web: Researchers fooled AI into ignoring stop signs using a cheap projector

The Next Web: Researchers fooled AI into ignoring stop signs using a cheap projector. “A trio of researchers at Purdue today published pre-print research demonstrating a novel adversarial attack against computer vision systems that can make an AI see – or not see – whatever the attacker wants. It’s something that could potentially affect self-driving vehicles, such as Tesla’s, that rely on cameras to navigate and identify objects.”

Leave a Reply

%d bloggers like this: