Attacking machine learning with adversarial examples

Re:Attacking machine learning with adversarial examples by dkarapetyan on Thursday February 16, 2017 @10:38PM (#13665728)

Except no amount of specially crafted noise will trick a human. If it looks like an octagon and is red then a human will interpret it as a stop sign. That's because I'd hope as a human you have a better conceptual understanding of what a stop sign is and what its intent is. Whereas none of the current crop of AI can claim any kind of understanding or even yield any kind of explanatory model.

Deep neural nets should really be called "really complicated composition of differentiable functions" and all the training algorithms should really be called "really complicated function root finding" because that's all these things are at the end of the day, a rats nest of functions with a billion knobs.

[ Parent | on HN ]

Re:Attacking machine learning with adversarial examples by tripzilch on Wednesday February 22, 2017 @05:28AM (#13704503)

> That's because I'd hope as a human you have a better conceptual understanding of what a stop sign is and what its intent is.

That's not the reason at all.

It's because if you add exactly the right type of specially crafted noise to an image of a stop sign such that, to a human, it looks like a panda--then who is going to be the arbiter that decides "No, it's still actually really an image of a stop sign and not a panda". The machine?

The real reason is the subjective nature of the perception of reality. With the advent of AI, all sorts of schools of philosophy that used to seem like useless navel-gazing are going to find some real important practical applications real soon. This is metaphysics and ontology. On a similar note (not in TFA), in the "friendly AI" debate, we're going to be looking real hard at the foundations of the philosophy of ethics (where does it really come from?), not just the teleological vs deontological (etc) debates we use to reason about law, politics, governance and appeasement of our "justice" instincts.

[ Parent | on HN ]

Re:Attacking machine learning with adversarial examples by emmab on Friday February 17, 2017 @05:58AM (#13667381)

> Except no amount of specially crafted noise will trick a human

Or quite possibly we just don't know how to construct the noise yet :P

[ Parent | on HN ]

Re:Attacking machine learning with adversarial examples by dkarapetyan on Friday February 17, 2017 @10:09AM (#13668686)

Well we do. Conspiracy theories are noise but not in the same category as pixel noise. When neural nets start falling for conspiracy theories then I'll start to worry about the coming singularity.

[ Parent | on HN ]

Re:Attacking machine learning with adversarial examples by koja86 on Friday February 17, 2017 @11:41AM (#13669555)

Might as well traffic signs were intentionally chosen as something human are good in classification of without any regard to machine learning algorithms (nonexistent at that time). Yet there are definitely tasks where specially crafted noise can fool humans. Think optical illusions or this car prototype camouflage: https://arstechnica.com/cars/2017/02/the-new-mclaren-720s-wi...

[ Parent | on HN ]