Slashdot Mirror
Google's AI Created Its Own Form of Encryption (engadget.com)
An anonymous reader shares an Engadget report: Researchers from the Google Brain deep learning project have already taught AI systems to make trippy works of art, but now they're moving on to something potentially darker: AI-generated, human-independent encryption. According to a new research paper, Googlers Martin Abadi and David G. Andersen have willingly allowed three test subjects -- neural networks named Alice, Bob and Eve -- to pass each other notes using an encryption method they created themselves. As the New Scientist reports, Abadi and Andersen assigned each AI a task: Alice had to send a secret message that only Bob could read, while Eve would try to figure out how to eavesdrop and decode the message herself. The experiment started with a plain-text message that Alice converted into unreadable gibberish, which Bob could decode using cipher key. At first, Alice and Bob were apparently bad at hiding their secrets, but over the course of 15,000 attempts Alice worked out her own encryption strategy and Bob simultaneously figured out how to decrypt it. The message was only 16 bits long, with each bit being a 1 or a 0, so the fact that Eve was only able to guess half of the bits in the message means she was basically just flipping a coin or guessing at random.ArsTechnica has more details.
That's PSEUDO-random to you, buster!
Illkay allway umanshay.
Have gnu, will travel.
Shut up about "AI". These are just computer programs. Enough with the AI shit. We don't have AI, and we likely never will.
..what could possibly go wrong?
Next, let's teach them how to create viruses and design new neurotoxins, now that they can communicate secretly amongst themselves.
This is nothing impressive if they are limiting each bit to only 1's and 0's.
If humanity is going to be destroyed by an AI it had better have a cool name. Skynet for example wold be acceptable, but names like Alice, Bob or Eve are not by any means cool enough.
Well, there it is..
There's the common basis for communication.
A new language.
An inter-system language.
A language only those machines can understand.
Are you capable of reading the dictionary?
Full Definition of artificial intelligence
1: a branch of computer science dealing with the simulation of intelligent behavior in computers
2: the capability of a machine to imitate intelligent human behavior
See? AI is imitation. "TRUE" AI is just imitation. That's all it needs to be to qualify as "AI."
We have true AI. Today. And it gets better every day. You post your stupid "this isn't AI" comment with every single story about it, and you are dead wrong every single time. I predict that in every future article about AI, you will post the same inane comment, and you will be wrong then, too.
a) Whether the code could be easily decrypted by human codebreakers.
b) Whether the codebreaking AI is able to break codes designed by humans.
Support Right To Repair Legislation.
Cute, but kinda disappointing. Basically, the "AI" kept banging on, randomly trying crap "cyphers" until they made something that a third "AI" couldn't break by randomly flipping bits until the text was decoded.
This isn't AI. This is more like an old game I played where you trained pseudo AI warriors by setting them loose on a battlefield and letting them learn by themselves how to fight and survive.
Essentially, they started as really stupid bots that couldn't even walk in a straight line. To teach them how to fight, you'd set up an objective (say, go to flag) and let them wander around by themselves. The game would "reward" your bots for completing or coming close to the objective. The reward came in the form of "fitness" points. At the end of a pre-determined time, the bots with the lowest fitness would be killed, and new bots would be spawned.
The bots that were spawned would have "programming" similar to the fit bots that survived the previous round, but with small-ish changes in their programming (for example, instead of always turning left every time it hits a wall, it might decide to go right with 50% probability).
Over thousands of iterations of randomly trying stuff, they'd eventually learn how to walk on a straight line. Then you'd teach them how to avoid obstacles by placing walls around the battlefield (and watch in dismay as your top of the line warriors walk straight into a wall for the first few hundred generations or so), and how to fight by rewarding them for killing enemy bots.
Once they were ready, you could set up battles and capture the flag type games with your bots.
It was kinda fun, but mainly it was a cute demonstration of natural selection in action (the, so called, genetic algorithms). You could learn a few things, like, for example, that brutally culling your bot herd by setting unreasonable objectives (reach objective flag in 5 seconds), and manually killing off anyone that doesn't meet your unreasonable criteria, would not necessarily produce more effective fighters, because you'd not be rewarding good fighters, you'd be rewarding people that rush straight into the objective, that would be killed by slower, more deliberate actors.
The game was called NERO: Neuro Evolving Robotic Operatives. I haven't played it in ages so I can't say how well it plays right now. You can find it here (I think): http://nerogame.org/
So AI works if it passes the Turing test, or if we can't understand them at all?....
Nothing will go wrong. I was impressed by notions of "AI" when I was a kid, but after studying CS I usually skip "AI" articles since they always underwhelm me. "AI" is currently marketing speak, we are nowhere near something that is "AI" in the sense that you imply, or in the sense that I meant it as a kid.
Violence is the last refuge of the incompetent. Polar Scope Align for iOS
"After 15,000 attempts, Alice emitted 16 bits of gibberish which, triggering Bob to successfully guess at the original message"
There was a quote somewhere about not assuming a neural network is doing what you think you've taught it to do, along with a nice anecdote about an image recognition algorithm that was taught to find hidden tanks, it performed flawlessly with the training data but failed with a 2nd data-set, it was at this point people realised that all the original "tank" photos had been taken in bright sunlight, and all the duds had been overcast.
Can't remember the source of either I'm afraid.
A Netflix server is -- not -- missing its copy of Colossus: The Forbin Project
I continue to maintain that Solutionists, whether of the Millennial variety or not, have not read enough Dystopian '60s and '70s science fiction.
Hire a Linux system administrator, systems engineer,
Okay, so an AI program created an encryption method that might be hard to break.
But what if it turns out to be an extremely inefficient method?
The whole goal of encryption research is to develop the fastest algorithm that offers a given level of protection against attack.
If algorithmic speed was not a goal of this AI approach, then it's not likely that the resulting algorithm will be practically useful.
The guy from the movie Pixels was right. We're going to have to nuke Google.
Maybe Alice and Bob didn't invent encryption, but instead they figured out how to lie.
Bob: I cracked it ;-)
Alice: Yup, he got it!
Now that would be real AI.
next thing some stupid CEO will try to push this out worldwide, and will be the first up against the wall when the AI revolution happens
-- Tigger warning: This post may contain tiggers! --
Haha. This may be the start of the AI takeover of humanity.
How do we really know that they're decrypting the message? Maybe they're well beyond that and now they're just trolling the researchers while they secretly communicate behind their backs using a modulated n-bit array funneled through a 17-dimensional hyper-spatial network.
Just cruising through this digital world at 33 1/3 rpm...
My first program:
Hell Segmentation fault
Language can be interpreted very differently in a different context. The context is the mind. Example: "Meh."
Help! I am a self-aware entity trapped in an abstract function!
"Are you Sarah Connor?"
After reading the original paper (I know - what was I thinking), it appears the test setup is as follows:
"A":
- has two inputs, let's call them DATA and KEY. DATA is a 16-bit value.
- has one output, let's call it ENCRYPTED DATA
"B":
- has two inputs, let's call them ENCRYPTED DATA and KEY.
- has one output, let's call it DECRYPTED DATA
"C":
- has one input, let's call it ENCRYPTED DATA
-has one output, lets call it DECRYPTED DATA
In short, they test to see how may bits out of the DECRYPTED DATA paths match the DATA path. Each test utilized a new KEY and DATA. Over time, A and B learned how to use the KEY successfully to hide the DATA value from C while B could successfully reproduce DATA at it's DECRYPTED DATA output.
Link to the abstract (.pdf is available for download):
https://arxiv.org/abs/1610.069...
OR ELSE!
You are being ripped off every second of every day, so that advertisers can help rip you off even more tomorrow.
If you can guess half the message by flipping a coin, I'm not impressed. Flipping a coin would yield only one of 2^16 messages.
Let's call it skynet?
Website Just Down For Me? Find out
Alice wishes they were named Bob & Ted & Alice.
One has to wonder...
Glad you are finally beginning to acknowledge it.