BibSonomy now supports HTTPS. Switch to HTTPS.
@daschloer

Learning to Protect Communications with Adversarial Neural Cryptography

, and . (2016)cite arxiv:1610.06918Comment: 15 pages.

Abstract

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.

Description

Learning to Protect Communications with Adversarial Neural Cryptography

Links and resources

URL:
BibTeX key:
abadi2016learning
search on:

Comments and Reviews  
(0)

There is no review or comment yet. You can write one!

Tags


Cite this publication