Re:Audio Adversarial Examples
by jchw on Tuesday January 30, 2018 @04:31PM
(#16269238)
I wonder if it's possible for an attack like this to work against the human brain.
[ Parent
| on HN ]
That's the purpose of magic[1], isn't it? Maybe one day magic tricks will be designed by AI. It'd be funny, since that would gave Arthur C. Clark famous quote ("any sufficiently advanced technology...") a whole new meaning.
Optical illusions have a similar effect. Also images that people can see in 2 different ways like the famous old/young woman example.
Re:Audio Adversarial Examples
by colechristensen on Tuesday January 30, 2018 @04:56PM
(#16269456)
Flashy cartoons give some people seizures.
I'd bet they could be engineered to affect a higher proportion of the population.
I'm pretty sure some alarms use a strobe light at a particular frequency combined with a loud 2kHz tone to discombobulate intruders. That's more sensory overload than an adversarial signal, though.
I'd expect a malicious adversarial example to be more like the ones discussed in Snow Crash or BLIT ( https://en.wikipedia.org/wiki/BLIT_(short_story) )
You could argue that cartoons or line drawings are "adversarial examples" that are reliably identified by the human visual system as representing a particular thing despite being quantitatively nothing like what they're meant to represent.
Remember the black/white gold/blue dress thing from a while back?
What do you mean? How would it look like?
Adding noise to a signal to cause it to be perceived unintuitively. It's possible that, as others pointed out, optical illusions are an example of this. But in actuality, if such a thing existed, I'm not sure we'd be able to tell it's adversarial.