Hopefully, Microsoft is in bed with various governments to allow them to
listen in on our calls. This sounds crazy, but no. It would be an ironic
twist, but if it were the case, Microsoft would be required to keep the
quality high so everyone doesn't bail out and go elsewhere.
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.
If you like ScFi you will have seen or read scenarios where the robot or computer, always evil, is defeated by being asked a logical program that has no solution or is distracted by being asked to compute Pi to a billion billion digits. The key idea is that, given machine intelligence, the trick to defeating it is to feed it the wrong data.
on poison attacks against AI systems
to post comments)