1. One way to make AI smarter is to have it learn from its environment. Cars of the future, for example, willbe better at reading street signs and avoiding pedestrians as they gain more experience. But hackers canexploit these systems with 'adversarial attacks": By subtly and precisely modifying an image, say, you canfool an AI into misidentifying it. A stop sign with a few stickers on it might be seen as a speed limit sign,for example. The new study reveals AI can be fooled into not only seeing something it shouldn't, but alsointo behaving in a way it shouldn't. (https://www.sciencemag.ory/news/2019/12/watch-ai-goalie-psych-out-its-opponent-most-hilarious-way)