Slashdot Mirror
Researchers Fooled a Google AI Into Thinking a Rifle Was a Helicopter (wired.com)
An anonymous reader shares a Wired report: Algorithms, unlike humans, are susceptible to a specific type of problem called an "adversarial example." These are specially designed optical illusions that fool computers into doing things like mistake a picture of a panda for one of a gibbon. They can be images, sounds, or paragraphs of text. Think of them as hallucinations for algorithms. While a panda-gibbon mix-up may seem low stakes, an adversarial example could thwart the AI system that controls a self-driving car, for instance, causing it to mistake a stop sign for a speed limit one. They've already been used to beat other kinds of algorithms, like spam filters. Those adversarial examples are also much easier to create than was previously understood, according to research released Wednesday from MIT's Computer Science and Artificial Intelligence Laboratory. And not just under controlled conditions; the team reliably fooled Google's Cloud Vision API, a machine learning algorithm used in the real world today. For example, in November another team at MIT (with many of the same researchers) published a study demonstrating how Google's InceptionV3 image classifier could be duped into thinking that a 3-D-printed turtle was a rifle. In fact, researchers could manipulate the AI into thinking the turtle was any object they wanted.
it is turtles all the way down.
So why can't the same perturbation techniques be used to fool neutral network based face recognition systems too?
Many humans are also easily fooled into thinking that this is just a plain brick wall:
http://cdn.playbuzz.com/cdn/d2...
If and when self-driving cars really become a thing, vandalism of street signs will probably have to be elevated to a felony with a mandatory minimums, even if no one gets hurt. It'll also have to be something where minors can be charged as adults because they're the ones who probably do the majority of it, and you know there will be teens who'll think it's funny to cause a 10 car pile up.
Donald Trump conned half the US electorate into believing he would be a competent president who'd bring change and reform that'd benefit the common man at the expense of the super wealthy. So it seems to me that artificial intelligence and natural intelligence suffer from the same flaw, feed them enough garbage data and they'll believe anything.
While the visual street signs will remain once driverless technology is >/= human performance, traffic signs and intersections will begin being fitted out with remote transmitters that communicate with your vehicle's on-board system, which will communicate with other vehicles on-board systems.
Happiness in intelligent people is the rarest thing I know.
Ernest Hemingway
I am proud, a proud citizen of the fruitful and glorious kingdom of the Netherland; soon to be holders and protectors of a global hegemony the likes never seen before. Our mighty ships, our mighty crews, they will set fire to the lands beyond. A fire no mortal can put out. Such is the power of the powerful nationstate "Holland": Saviours of the Just, protectors of the Golden Child.
What's in the pic?
Many believe their imaginary friend is real. just because they where told by others that that imaginary friend is real. OTOH we won't believe a sign that said a bench has wet paint and we need to
Now that the system knows it was fooled. Will it be fooled again? Because "Fool me twice and I won't be fooled again."
I do not think the system was actually "fooled" It was taught the wrong thing. If anything, it was mislead. Just like you can tell a kid that the candy came out of its ear or you stole its nose.
Don't fight for your country, if your country does not fight for you.
Seriously - The headline says it thought a rifle was a helicopter. The summary said it thought a turtle was a rifle.
WTF?
All of these vision AIs are programmed backwards -- for convenience. This random object looks "more like" a speed limit sign and "less like" a stop sign. Great. No body cares about how much "like" something another something appears.
You can ask any 10-year old. A stop sign is a red octagon. Any 16-year old will say it also has a white border, and white lettering in the middle. Any experienced driver will add that it appears at some sort of intersection, obstruction, or event, alongside a narrow road.
Now, if you see a red octagon, and you stop, and it turns out to be a giant lollipop, then that's good. Because a giant lollipop on the road is absolutely acting as a stop sign.
If something isn't a red octagon, then it's definitely not a stop sign.
The problem here is that google's vision AI doesn't identify an sight according to what defines a stop sign -- a red octagon on the side of the road. That's because it's highly stupid.
And the question really comes down to something much simpler. If I put a big square sign on the side of the road, blue, with yellow lettering, that says "please pause, thank you", will google treat it as a stop sign? Good bet that any driver who sees it (and can certainly be forgiven for not noticing it) will stop.
Conversely, on a highway, at 120kph, if I put a real stop sign on the side of the road, will google treat it as a stop sign? No human driver is going to slam on the brakes.
Google's not thinking. Therefore, it ain't an AI. It surely "looks like" an AI, but it's not an AI. It uses collected intelligence to determine what the object is, but it doesn't use its own intelligence to make decisions. It doesn't make decisions at all.
Show me a vision system that can take any photograph of any road, and decide whether or not it should stop the car. Doesn't need to be right or wrong, correct or incorrect, it just needs to make a decision, reliably, that makes sense. See, if it can do that, "reliably", then we can change the signs for them. We chose the signs for us for a reason. Humans see red first, so stop signs are red. If machines have trouble with octagons, and love purple, then we can give them that instead. Dual signage is common in multi-lingual communities.
But these shitty AI systems are much worse. They don't even make their classifications reliably -- because the more data they collect, the most they distract themselves. So a guaranteed "this is a stop sign, 100%" can change a year later, as it "learns", such that the very same stop sign is now only 80%. There's no fortification. There's no stubbornness. That's a problem.
There's bound to be humans fooled by adversarial examples too. Who wants to do those studies.
...is going to be the huge number of cats named Guacamole for the lols.
Rifle is fine
playmoney.me - The free alternative to paper board game play money
Kinney gets machine gunned.
https://media.giphy.com/media/FvaTwHY7YDn20/giphy.gif
Optical illusions work because our visual system takes certain shortcuts to reduce the amount of processing needed to identify what it is we're looking at. e.g. We assume diagonal lines are 3-dimensional, leading to errors when we view a 2D object with diagonal lines. The only information actually provided was the horizontal line + 2 diagonal lines. Our brains extrapolated the nonexistent 3D nature of the object to create the error. (The top line looks like the the edge of a box viewed from the inside, so our brain concludes the line is further away and thus bigger than it appears; the bottom line looks like the edge of a box viewed from the outside, so our brain concludes the line is closer and thus smaller than it appears.) Likewise, the computer vision AI makes the turtle/rifle error because it's extrapolating from its very limited information subset to determine if the object is a turtle or a rifle.
These sorts of errors disappear as you add more information, thus reducing the amount of extrapolation needed. I was driving on a rural highway at night when suddenly it seemed like the road was twisting and warping. This went on for about 10 seconds until I moved into an area with fewer trees, and I realized what I thought were billboards in the distance were actually boxcars on a moving train. My brain had been assuming they were fixed points in space, when in fact they were moving. So initially it erroneously concluded the billboards were static and the road was warping, but the moment I recognized them as boxcars my brain correctly realized the "billboards" were moving and the road was static.
So in these early stages of visual AI, we're going to encounter a lot of these errors. But as the AI becomes more sophisticated and able to take into account more contextual information, these errors will begin to disappear. They probably won't disappear entirely, because you can only glean so much information from a static photo. But for real-life applications like security, the turtle/rifle error is highly unlikely to happen once the AI starts comparing the questionable object in multiple frames in a video instead of a single frame, or starts comparing it from multiple viewpoints provided by multiple cameras.
Algorithms, unlike humans, are susceptible to a specific type of problem called an "adversarial example." These are specially designed optical illusions that fool computers[...]
In other words, just like the optical illusions that humans are notoriously susceptible to? Jesus. The phenomenon is actually somewhat interesting, but maybe you shouldn't start out with a blatant self-contradictory assertion.
The 2016 election is the result of three decades of adversarial examples being fed to the American public
So basically, AI are as smart as Trump voters, now? I guess we haven't come as far as we'd thought.
As someone who sexually identifies as an attack helicopter, I am concerned about the health risks this could pose.