In recent years, the media have been paying increasing attention to adversarial examples, input data such as images and audio that have been modified to manipulate the behavior of machine learning algorithms. Stickers pasted on stop signs that cause computer vision systems to mistake them for speed limits; glasses that fool facial recognition systems, turtles that get classified as rifles — these are just some of the many adversarial examples that have made the headlines in the past few years. There’s increasing concern about the cybersecurity implications of adversarial examples, especially as machine learning systems continue to become an important component of many…

This story continues at The Next Web