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.

Comments

Still better than humans

[houghi]

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.

Re:Bah....

[Anonymous Coward]

Here we have a convenient demonstration of Trump-supporter Hypocritical Hysteria. A common, unimportant, Internet troll makes a minor statement of no consequence, no particular imagination, and no significant castigatorial qualities, and yet the unrepentant apologist for Trump can't resist trying to make it out to be a significant demonstrator of some problem among his opposition so he finds himself forced to inflate its character to a point of absurdity. That's a consistent pattern among the allies of Trump, the tendency to make mountains out of ant hills. Consider folks, these folks spewing their disingenuous defensiveness are the same ones who told us their rule was the only thing that would save us from some oncoming tragic disaster such as effects of the devastating War on Christmas. But if there was actually a problem, would any diligent savior with common sense be wasting their time with such unimportant minor details, or is it just possible that they're blowing smoke in order to distract us from the e-mails they're trying to burn so the ongoing investigation into their treacherous perfidy isn't revealed?

When will they ever start to clean their own houses? Can they not purge their own distractions? And no, you can't count the defeat of Roy Moore, he only barely lost, and few of the people who find themselves in association with Trump could keep up the charade of pretending to oppose Roy Moore, and Trump himself was indignant at the thought of abandoning a person on grounds of integrity. Didn't want to set a precedent, I believe. Can't have Republicans standing on genuine principle after all. Much better to burn down the Windmills because they're a threat to nature unlike the soot-spewing coal-burning power-plants that are doing as God and Jesus intended.

Re:Google should know already...

[jellomizer]

The key problem with AI, is its trust in in its sources. They havn't programmed in a silly algorithm yet. When kids are learning to process the world. Kids learn when things are in the wrong context then it is probably silly or just wrong. Even if it from a trusted source, a kid will laugh at their parent if they are saying something that is contradicting their view of the world. Such as when the parent is playing with the kid, they substitute a toy car for a doll, and play with the car like a doll. The child find this amusing because the context is all wrong. The AI algorithm seeing this, would just say this toy probably of usage has expanded to be used as a doll so it must be a doll. There is no questioning saying "no, that is not how you play with that toy". it will take the source as factual and just add it to its list.

Re: Vandalism will have to be punished harder

[I'm New Around Here]

Do stupid crimes, pay stupid prices.

If anyone wants my sympathy because they got busted for drugs, tough luck. Drugs are illegal, and many state/city/federal prosecutors punish harshly for them. If drug users are too stupid to figure that out, that's their fault.

And, yes, I know several drug users, any one of which could end up in jail for years if busted. And I have said that to them,