PRA on International Press

Poison Attacks Against Machine Learning.

With AI systems becoming more common, we have to start worrying about security. A network intrusion may be all the more serious if it is a neural net that is affected. New results indicate that it may be easier than we thought to provide data to a learning program that causes it to learn the wrong things. Three researchers, Battista Biggio (Italy) Blaine Nelson and Pavel Laskov (Germany), have found a way to...