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.

Robot Secret
Psst! (SARAH HOLMUND/DIGITAL STORM VIA SHUTTERSTOCK)


Google’s Deep Brain team has been working on artificial intelligence from a variety of angles. Last May, for example, their Magenta project attempted to teach AI how to create art and music.

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.

(GOOGLE)

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.

COVID-19 amplified America’s devastating health gap. Can we bridge it?

The COVID-19 pandemic is making health disparities in the United States crystal clear. It is a clarion call for health care systems to double their efforts in vulnerable communities.

Willie Mae Daniels makes melted cheese sandwiches with her granddaughter, Karyah Davis, 6, after being laid off from her job as a food service cashier at the University of Miami on March 17, 2020.

Credit: Joe Raedle/Getty Images
Sponsored by Northwell Health
  • The COVID-19 pandemic has exacerbated America's health disparities, widening the divide between the haves and have nots.
  • Studies show disparities in wealth, race, and online access have disproportionately harmed underserved U.S. communities during the pandemic.
  • To begin curing this social aliment, health systems like Northwell Health are establishing relationships of trust in these communities so that the post-COVID world looks different than the pre-COVID one.
Keep reading Show less

Mathematical model shows how the Nazis could have won WWII's Battle of Britain

With just a few strategical tweaks, the Nazis could have won one of World War II's most decisive battles.

Photo: Heinrich Hoffmann/ullstein bild via Getty Images
Politics & Current Affairs
  • The Battle of Britain is widely recognized as one of the most significant battles that occurred during World War II. It marked the first major victory of the Allied forces and shifted the tide of the war.
  • Historians, however, have long debated the deciding factor in the British victory and German defeat.
  • A new mathematical model took into account numerous alternative tactics that the German's could have made and found that just two tweaks stood between them and victory over Britain.
Keep reading Show less

The neoliberal era is ending. What comes next?

The next era in American history can look entirely different. It's up to us to choose.

Videos
  • The timeline of America post-WWII can be divided into two eras, according to author and law professor Ganesh Sitaraman: the liberal era which ran through the 1970s, and the current neoliberal era which began in the early 1980s. The latter promised a "more free society," but what we got instead was more inequality, less opportunity, and greater market consolidation.
  • "We've lived through a neoliberal era for the last 40 years, and that era is coming to an end," Sitaraman says, adding that the ideas and policies that defined the period are being challenged on various levels.
  • What comes next depends on if we take a proactive and democratic approach to shaping the economy, or if we simply react to and "deal with" market outcomes.

Keep reading Show less

10 ways to prepare for rise of intelligent machines – MIT study

A new MIT report proposes how humans should prepare for the age of automation and artificial intelligence.

An employee cleans around early test robot displays at the Akin Robotics factory on March 15, 2018 in Konya, Turkey.

Photo by Chris McGrath/Getty Images
Technology & Innovation
  • A new report by MIT experts proposes what humans should do to prepare for the age of automation.
  • The rise of intelligent machines is coming but it's important to resolve human issues first.
  • Improving economic inequality, skills training, and investment in innovation are necessary steps.
Keep reading Show less
Scroll down to load more…
Quantcast