Alice, Bob, and Eve Are Neural Networks. And They Have Secrets.
Google’s Deep Brain team watched neural nets learn to develop their own encryption.
Magenta art (GOOGLE)
A lot of what the team does is fairly abstruse to the non-scientist, but they’ve just announced something we can all understand, and it’s a doozy: Two Deep Brain scientists, Martín Abadi and David Andersen, recently tasked two neural nets with keeping a secret from a third. What they found was that “neural networks can learn to protect the confidentiality of their data from other neural networks: they discover forms of encryption and decryption, without being taught specific algorithms for these purposes.”
Neural nets — artificial-neuron-based systems — aren’t designed for cryptography, so Abadi and Andersen had been curious to see if neural nets could teach themselves to master it.
The neural nets were named Alice, Bob, and Eve. In the experiment, Alice was set the task of sending Bob message only he could read. (I’m going to use human pronouns here instead of the more correct “it” to make this easier to follow.) The two neural nets shared a numeric encryption key to use. Eve had no key, and was left to her own devices to figure out the message.
In this diagram, P is the original message and K is the key Alice and Bob shared. C is the encrypted message Alice produced, which is received by Bob and Eve, who each attempted to decipher it. (GOOGLE)
At first Eve was pretty good at it, but as Alice and Bob got more clever during 15,000 attempts, Eve’s failure rate remained consistently as Bob and Alice’s communication began to consistently succeed.
Alice and Bob got into some interestingly odd encryption tricks that leveraged calculations that human-generated encryption schemes don’t use. Much like the different logic with which Google’s AlphaGo surprised and defeated human Go master Fan-Hui last January, Alice and Bob did things to hide their messages that might never occur to a human.
While it’s easy to see that AI-devised encryption might ensure the integrity of machine-to-machine communications during secure multi-device operations, it’s also a little worrisome. Alice and Bob are the first neural nets who’ve kept secrets from their programmers. That we know of.
- The meaning of the word 'confidence' seems obvious. But it's not the same as self-esteem.
- Confidence isn't just a feeling on your inside. It comes from taking action in the world.
- Join Big Think Edge today and learn how to achieve more confidence when and where it really matters.
- Bad outcomes get criticized as evidence of bad decisions, but that's not necessarily so.
- Here, poker pro Annie Duke desribes a simple thought experiment that separates decisions from outcomes.
- It is quite possible to make a very good decision that, due to external factors, results in a bad outcome.
Decide to Play Great Poker: A Strategy Guide to No-Limit Texas Hold '’Em
American geneticists take a stand against the misuse of their science by racists.
- The largest society of geneticists decries the distortion of ideas by racists.
- Science does not support the concept of race.
- Race is a social construct, explain the scientists.
If you're lacking confidence and feel like you could benefit from an ego boost, try writing your life story.
In truth, so much of what happens to us in life is random – we are pawns at the mercy of Lady Luck. To take ownership of our experiences and exert a feeling of control over our future, we tell stories about ourselves that weave meaning and continuity into our personal identity.
SMARTER FASTER trademarks owned by The Big Think, Inc. All rights reserved.