View source for Learning to Protect Communications with Adversarial Neural Cryptography (nonfiction)

[[File:Neural_network_cryptography_diagram.png|thumb|Neural network cryptography diagram.]]'''''Learning to Protect Communications with Adversarial Neural Cryptography'''''  is a research paper by Martín Abadi, David G. Andersen of Google Brain.

Abstract:

<blockquote>We ask whether neural networks can learn to use secret keys to protect information from other neural networks. Specifically, we focus on ensuring confidentiality properties in a multiagent system, and we specify those properties in terms of an adversary. Thus, a system may consist of neural networks named Alice and Bob, and we aim to limit what a third neural network named Eve learns from eavesdropping on the communication between Alice and Bob. We do not prescribe specific cryptographic algorithms to these neural networks; instead, we train end-to-end, adversarially. We demonstrate that the neural networks can learn how to perform forms of encryption and decryption, and also how to apply these operations selectively in order to meet confidentiality goals.</blockquote>

It was published in October 2016.

== In the News ==

<gallery>
</gallery>

== Fiction cross-reference ==

== Nonfiction cross-reference ==

* [[Artificial intelligence (nonfiction)]]
* [[Cryptography (nonfiction)]]

External links:

* [https://arxiv.org/abs/1610.06918 Learning to Protect Communications with Adversarial Neural Cryptography] @ Cornell University Library
* [https://www.engadget.com/2016/10/28/google-ai-created-its-own-form-of-encryption/ Google's AI created its own form of encryption]
* [https://tech.slashdot.org/story/16/10/28/1520233/googles-ai-created-its-own-form-of-encryption Google's AI Created Its Own Form of Encryption ] @ Slashdot

[[Category:Nonfiction (nonfiction)]]
[[Category:Artificial intelligence (nonfiction)]]
[[Category:Cryptography (nonfiction)]]

{{DISPLAYTITLE:''{{FULLPAGENAME}}''}}