As smart devices permeate our lives, Google sends up a red flag and shows how the underlying systems can be attacked. The implications are huge in a world growing more saturated with so-called machine intelligence. Google researcher Nicholas Carlini gave attendees an overview of the possible attack vectors that could not only flummox machine-learning systems, but also extract sensitive information from large data sets inadvertently. With the right camouflaged audio, an adversary could command an Android phone to do any number of risky tasks.
Source: https://threatpost.com/machine-learning-dark-side/142616/