Google's AIs learn how to encrypt their own messages

Neural networks could create encryption that becomes stronger as you hack it

A Google AI system learned how to build its own encryption key, and to make it stronger after being attacked.

Google's deep learning unit, Brain, built two neural networks, 'Alice' and 'Bob', to test whether they could create their own encryption algorithms and communicate without their messages being intercepted.

Alice sent Bob an encrypted message consisting of 16 zeroes and ones, and Bob decrypted it while Eve was intercepting this information and also trying to decrypt the message, according to the New Scientist.

Advertisement - Article continues below

Alice was able to learn from its failed attempts that were decrypted by Eve, and alter the encrypted message to prevent Eve from decoding it the following time.

The results of this experiment saw the neural networks successfully create a new encryption key advanced enough that even Eve could not break it. The way in which the encryption was devised by the two neural networks is so complex that even the researchers struggle to understand it.

These findings could be important in future, where neural networks could help AIs create encryptions that learn and become stronger as hackers try to break them, ultimately making them ideal for cybersecurity.

Featured Resources

Top 5 challenges of migrating applications to the cloud

Explore how VMware Cloud on AWS helps to address common cloud migration challenges

Download now

3 reasons why now is the time to rethink your network

Changing requirements call for new solutions

Download now

All-flash buyer’s guide

Tips for evaluating Solid-State Arrays

Download now

Enabling enterprise machine and deep learning with intelligent storage

The power of AI can only be realised through efficient and performant delivery of data

Download now
Advertisement

Recommended

Visit/security/355013/10-quick-tips-to-identifying-phishing-emails
Security

10 quick tips to identifying phishing emails

16 Mar 2020
Visit/business-strategy/mergers-and-acquisitions/354941/panda-security-to-be-acquired-by-watchguard
mergers and acquisitions

Panda Security to be acquired by WatchGuard

9 Mar 2020
Visit/technology/artificial-intelligence-ai/354766/mit-develops-ai-tech-to-edit-outdated-wikipedia
artificial intelligence (AI)

MIT develops AI tech to edit outdated Wikipedia articles

13 Feb 2020
Visit/security/internet-security/354417/avast-and-avg-extensions-pulled-from-chrome
internet security

Avast and AVG extensions pulled from Chrome

19 Dec 2019

Most Popular

Visit/infrastructure/server-storage/355118/hpe-warns-of-critical-bug-that-destroys-ssds-after-40000-hours
Server & storage

HPE warns of 'critical' bug that destroys SSDs after 40,000 hours

26 Mar 2020
Visit/software/355113/companies-offering-free-software-to-fight-covid-19
Software

These are the companies offering free software during the coronavirus crisis

25 Mar 2020
Visit/software/video-conferencing/355138/zoom-beaming-ios-user-data-to-facebook-for-targeted-ads
video conferencing

Zoom beams iOS user data to Facebook for targeted ads

27 Mar 2020
Visit/cloud/355098/ibm-dedicates-supercomputing-power-to-coronavirus-researchers
high-performance computing (HPC)

IBM dedicates supercomputing power to coronavirus research

24 Mar 2020